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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35075
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming languages and coding practices

    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
    326
    +0.14
    0.6%
    371
    +0.11
    0.4%
    31
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.14
    0.05
    176
    +0.11
    0.04
    167
    +0.11
    -0.03
    Negative Logits
     Leth
    -0.82
     Malk
    -0.82
     Lauder
    -0.80
     Gillespie
    -0.78
    Redd
    -0.77
     circulation
    -0.76
     Baltic
    -0.75
     Icelandic
    -0.74
     Incarn
    -0.73
     CoC
    -0.73
    POSITIVE LOGITS
    #$
    1.27
    @@@@@@@@
    1.20
    home
    1.03
    param
    1.01
    Override
    0.99
    gmail
    0.98
    include
    0.96
    import
    0.94
    echo
    0.94
    achable
    0.94
    Activations Density 4.719%

    No Known Activations