© 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 EvalsExportsAPI 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. 33773
    Prev
    Next
    INDEX
    Explanations

    text related to programming and technical instructions

    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
    +0.24
    1.3%
    457
    +0.08
    0.4%
    528
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.24
    0.23
    154
    +0.08
    0.27
    23
    +0.08
    0.25
    Negative Logits
     juggling
    -0.64
     Juda
    -0.62
     incorpor
    -0.60
     velvet
    -0.57
    rons
    -0.56
     stuffing
    -0.55
     spiral
    -0.55
     rotating
    -0.54
     remission
    -0.53
     vom
    -0.52
    POSITIVE LOGITS
    */
    0.63
    ï¸
    0.59
    ¬
    0.58
     Mumbai
    0.57
    DT
    0.57
    ãĢij
    0.57
    >>
    0.55
     CONT
    0.55
     âĢ
    0.54
    audi
    0.54
    Activations Density 11.875%

    No Known Activations