© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 4054
    Prev
    Next
    INDEX
    Explanations

    information related to comments or updates within a text dataset

    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
    333
    +0.12
    0.5%
    447
    +0.11
    0.5%
    268
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.12
    0.07
    314
    +0.11
    -0.04
    6
    +0.10
    0.13
    Negative Logits
    ftime
    -0.72
     bos
    -0.68
    igion
    -0.66
     toget
    -0.65
     cryst
    -0.64
     bast
    -0.64
     te
    -0.64
     compan
    -0.64
    pless
    -0.64
     wal
    -0.63
    POSITIVE LOGITS
     Description
    0.85
    Compl
    0.70
    Mine
    0.70
    ITION
    0.69
     Kramer
    0.68
     Towards
    0.68
    Recommend
    0.68
     Conclusion
    0.67
    verages
    0.67
    orthy
    0.67
    Activations Density 7.013%

    No Known Activations