© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22784
    Prev
    Next
    INDEX
    Explanations

    situations involving casualties and incidents related to fire or violence

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.30
    1.4%
    5
    +0.11
    0.5%
    225
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.30
    0.05
    362
    +0.11
    0.06
    481
    +0.09
    0.07
    Negative Logits
    endas
    -0.77
     Gins
    -0.76
     royalties
    -0.73
    ħĭ
    -0.73
     Parables
    -0.72
     patents
    -0.72
    izons
    -0.72
     monog
    -0.70
     envy
    -0.69
     counsel
    -0.68
    POSITIVE LOGITS
     gunfire
    1.27
     disturbance
    1.19
     explosions
    1.17
     explosion
    1.11
     gunshots
    1.11
     gunmen
    1.10
     gunman
    1.10
     disturbances
    1.09
     detonated
    1.06
     carnage
    1.04
    Activations Density 0.684%

    No Known Activations