© 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 EvalsExportsinterp-engineNEWAPI 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. 32413
    Prev
    Next
    INDEX
    Explanations

    news captions from articles related to protests or public demonstrations

    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
    386
    +0.16
    0.7%
    717
    +0.15
    0.7%
    739
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.21
    6
    +0.15
    0.14
    373
    +0.12
    -0.11
    Negative Logits
    ught
    -0.92
    axis
    -0.74
    omics
    -0.74
     conversion
    -0.73
     endeavour
    -0.72
    cham
    -0.71
    intend
    -0.68
     mart
    -0.66
    sed
    -0.66
    sole
    -0.66
    POSITIVE LOGITS
    uments
    0.95
     Execution
    0.88
     Thumbnails
    0.87
     Caption
    0.85
     Close
    0.84
    actionDate
    0.81
     Loading
    0.79
     ï
    0.78
    anse
    0.76
    ainers
    0.74
    Activations Density 3.774%

    No Known Activations