© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8808
    Prev
    Next
    INDEX
    Explanations

    references to political and societal issues

    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
    314
    +0.16
    0.8%
    113
    +0.11
    0.5%
    676
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.16
    0.05
    113
    +0.11
    0.04
    676
    +0.10
    0.04
    Negative Logits
    aceutical
    -0.75
    FTWARE
    -0.63
    SHIP
    -0.56
    HTTP
    -0.55
    Ts
    -0.55
     motions
    -0.55
     thereof
    -0.55
    QL
    -0.54
    behavior
    -0.54
    Admin
    -0.54
    POSITIVE LOGITS
     least
    1.26
    yp
    1.10
     odds
    1.00
     logger
    0.97
     pains
    0.94
    onement
    0.91
     risk
    0.90
    roph
    0.89
     stake
    0.86
     fault
    0.85
    Activations Density 0.087%

    No Known Activations