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. 4340
    Prev
    Next
    INDEX
    Explanations

    statistical and financial information

    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
    481
    +0.16
    0.8%
    447
    +0.13
    0.6%
    589
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.16
    -0.03
    127
    +0.13
    0.09
    326
    +0.10
    0.29
    Negative Logits
    avascript
    -0.59
    Ô
    -0.57
    :(
    -0.54
     snowball
    -0.54
     craft
    -0.54
     liqu
    -0.52
     redef
    -0.51
     dro
    -0.51
     veto
    -0.51
     snipp
    -0.50
    POSITIVE LOGITS
    .),
    1.22
    .).
    1.22
    ),
    1.22
    ).
    1.20
    /)
    1.13
    );
    1.10
    %).
    1.10
    .)
    1.09
    %)
    1.06
    )."
    1.05
    Activations Density 15.754%

    No Known Activations