© 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. 32715
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and reflections on various topics

    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
    1.6%
    393
    +0.19
    1.0%
    86
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.31
    0.20
    43
    +0.19
    0.17
    393
    +0.10
    0.26
    Negative Logits
    ved
    -0.62
    ver
    -0.60
    ãĥ¥
    -0.59
    iple
    -0.59
    utive
    -0.57
    ety
    -0.57
    olves
    -0.57
    cel
    -0.57
    riages
    -0.56
    untarily
    -0.56
    POSITIVE LOGITS
     namely
    1.14
     albeit
    1.04
     though
    0.94
     huh
    0.91
     although
    0.89
     viz
    0.89
     wherein
    0.86
     lest
    0.83
     however
    0.81
     whereby
    0.80
    Activations Density 9.228%

    No Known Activations