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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13465
    Prev
    Next
    INDEX
    Explanations

    animals and their associated habitats and characteristics

    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
    +0.31
    1.2%
    549
    +0.13
    0.5%
    403
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.31
    0.12
    442
    +0.13
    0.10
    232
    +0.12
    0.08
    Negative Logits
    soDeliveryDate
    -0.90
     Azerb
    -0.85
    æ©
    -0.84
    isSpecialOrderable
    -0.83
     Savings
    -0.80
    é¾įå¥ij士
    -0.80
    mberg
    -0.79
    stanbul
    -0.77
    iband
    -0.77
    ãĥ´ãĤ¡
    -0.76
    POSITIVE LOGITS
     carc
    1.39
     beetle
    1.18
     species
    1.18
    fish
    1.10
     beetles
    1.05
     hunter
    1.05
     pup
    1.05
     larvae
    1.04
     habitat
    1.04
     paws
    1.03
    Activations Density 10.136%

    No Known Activations