© 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. 18580
    Prev
    Next
    INDEX
    Explanations

    violence-related incidents

    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
    43
    +0.12
    0.5%
    719
    +0.10
    0.5%
    255
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.04
    178
    +0.10
    0.05
    255
    +0.10
    0.04
    Negative Logits
    soDeliveryDate
    -0.82
    leground
    -0.77
    adian
    -0.76
    weekly
    -0.75
    CHAT
    -0.75
    peak
    -0.73
    paren
    -0.73
    igmatic
    -0.72
     renaissance
    -0.71
    ante
    -0.71
    POSITIVE LOGITS
     injuring
    1.37
     wounding
    1.20
     injure
    1.17
     ejected
    1.07
     causing
    1.01
     screamed
    1.01
     Luckily
    0.99
     eject
    0.95
     resulting
    0.95
     incapac
    0.94
    Activations Density 0.308%

    No Known Activations