© 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. 36574
    Prev
    Next
    INDEX
    Explanations

    references to numbers or numerical sequences

    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
    +0.15
    0.9%
    71
    +0.08
    0.5%
    240
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.15
    0.08
    748
    +0.08
    0.05
    183
    +0.07
    0.08
    Negative Logits
    ACTION
    -0.52
    lance
    -0.52
     Rica
    -0.51
    Hub
    -0.51
    PI
    -0.50
    hub
    -0.49
    berman
    -0.49
    AIN
    -0.48
    hammad
    -0.48
    TM
    -0.48
    POSITIVE LOGITS
    eenth
    1.16
    een
    1.14
    teen
    0.94
    fold
    0.92
    teenth
    0.92
     hundred
    0.89
     thousand
    0.83
    ieth
    0.82
     months
    0.74
    aciously
    0.70
    Activations Density 6.426%

    No Known Activations