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

    Neuronpedia

    Jacobian LensNEW
    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. 33400
    Prev
    Next
    INDEX
    Explanations

    descriptions of items with specific foldable features

    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
    +0.16
    0.8%
    114
    +0.11
    0.5%
    78
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.16
    608
    +0.11
    0.21
    636
    +0.10
    0.09
    Negative Logits
    ega
    -0.71
    Demand
    -0.67
    vez
    -0.67
     Appears
    -0.65
    oice
    -0.64
    FTWARE
    -0.63
     Achievement
    -0.62
    nesota
    -0.62
    penter
    -0.61
     indo
    -0.61
    POSITIVE LOGITS
    ername
    0.89
    leaf
    0.73
    lift
    0.73
     folded
    0.72
     folding
    0.69
     fold
    0.68
    sheet
    0.67
    ener
    0.67
    glers
    0.67
    cloth
    0.65
    Activations Density 13.613%

    No Known Activations