© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 6327
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance or resistance to pressure or convention

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    9
    +0.12
    0.6%
    407
    +0.11
    0.5%
    611
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.12
    0.03
    70
    +0.11
    0.03
    611
    +0.11
    0.03
    Negative Logits
    kson
    -0.73
    anon
    -0.70
    pelling
    -0.69
    MSN
    -0.64
    iewicz
    -0.63
    updated
    -0.63
    cards
    -0.63
     headlines
    -0.62
    effects
    -0.61
    rification
    -0.60
    POSITIVE LOGITS
    aciously
    1.15
     knees
    1.03
     toe
    0.99
     shoulders
    0.97
     deaf
    0.90
     politely
    0.89
    heit
    0.88
     knee
    0.85
     miser
    0.85
     willingly
    0.81
    Activations Density 0.131%

    No Known Activations