© 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 3072
    9. 8-RES_FS3072-JB
    11. 245
    Prev
    Next
    INDEX
    Explanations

    information related to crime incidents and incidents of violence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    516
    +0.12
    0.5%
    187
    +0.10
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.12
    0.11
    121
    +0.10
    0.13
    47
    +0.10
    0.11
    Negative Logits
     cures
    -0.91
     optim
    -0.88
     trillions
    -0.81
    optim
    -0.78
     immortality
    -0.74
     ç¥ŀ
    -0.74
     royalty
    -0.74
     resolutions
    -0.73
     legions
    -0.72
    olkien
    -0.72
    POSITIVE LOGITS
     burglary
    1.23
     robbery
    1.18
     police
    1.11
     gunfire
    1.09
     altercation
    1.09
     burgl
    1.09
    Police
    1.07
     SUV
    1.05
     gunshots
    1.04
    Officers
    1.03
    Activations Density 3.711%

    No Known Activations