© 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
    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. 13771
    Prev
    Next
    INDEX
    Explanations

    function names and code structures within a programming context

    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
    127
    +0.11
    0.6%
    223
    +0.11
    0.5%
    311
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.28
    326
    +0.11
    0.26
    99
    +0.10
    0.11
    Negative Logits
    ewater
    -0.73
     Lank
    -0.69
    jo
    -0.65
    noon
    -0.64
    rolled
    -0.64
     Debor
    -0.62
    agement
    -0.61
    angan
    -0.61
    mit
    -0.61
    ciation
    -0.61
    POSITIVE LOGITS
    onomic
    0.71
    actory
    0.68
    onom
    0.68
    ranch
    0.68
    ivated
    0.65
    ivation
    0.65
    usable
    0.62
    izont
    0.62
    umin
    0.62
     fmt
    0.62
    Activations Density 9.738%

    No Known Activations