© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36506
    Prev
    Next
    INDEX
    Explanations

    different items such as clothing, food ingredients, and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    1.5%
    640
    +0.23
    1.2%
    481
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.58
    6
    +0.23
    0.31
    160
    +0.18
    0.35
    Negative Logits
     freel
    -0.72
    terday
    -0.69
     previously
    -0.67
     increasingly
    -0.66
     superf
    -0.65
     shrinking
    -0.65
     halfway
    -0.65
     governors
    -0.65
     scrap
    -0.64
     board
    -0.64
    POSITIVE LOGITS
    --------------------------------------------------------
    1.14
    ----------------------------------------------------------------
    1.12
    */
    1.09
    ================================================================
    1.05
    LESS
    0.95
    Therefore
    0.94
    """
    0.93
    ********************************
    0.91
    ________________________________________________________________
    0.90
    However
    0.89
    Activations Density 14.388%

    No Known Activations