Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13231
    Prev
    Next
    INDEX
    Explanations

    references to time periods or specific dates

    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
    1.4%
    423
    +0.07
    0.4%
    553
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.24
    0.09
    377
    +0.07
    0.17
    485
    +0.07
    0.11
    Negative Logits
    fect
    -0.61
    onal
    -0.57
    regate
    -0.56
    henko
    -0.56
     RTX
    -0.56
     Hits
    -0.55
    edly
    -0.55
    agate
    -0.54
     bidder
    -0.52
    adium
    -0.51
    POSITIVE LOGITS
    adays
    0.70
    pring
    0.65
    hift
    0.65
    days
    0.63
    hops
    0.55
    abouts
    0.54
     everywhere
    0.51
    paces
    0.51
    creen
    0.51
    TON
    0.50
    Activations Density 10.592%

    No Known Activations