© 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. 32281
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rib"

    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
    52
    +0.13
    0.6%
    326
    +0.13
    0.6%
    484
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.20
    349
    +0.13
    0.07
    52
    +0.13
    0.08
    Negative Logits
     Sunny
    -0.83
    terday
    -0.80
     GOODMAN
    -0.78
     SOS
    -0.77
    eanor
    -0.75
     Ceres
    -0.75
     Claus
    -0.73
    ĨĴ
    -0.71
    idad
    -0.68
     Edison
    -0.67
    POSITIVE LOGITS
    bons
    1.60
    bed
    1.13
    bing
    1.10
    bent
    1.02
    bon
    0.98
    bones
    0.93
    bles
    0.92
    bled
    0.91
     rib
    0.90
    ald
    0.90
    Activations Density 6.498%

    No Known Activations