© 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. 20889
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court cases and legal hearings

    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
    677
    +0.11
    0.5%
    136
    +0.10
    0.4%
    34
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.11
    0.05
    310
    +0.10
    0.05
    223
    +0.10
    0.04
    Negative Logits
     Built
    -0.67
     shipped
    -0.66
     exported
    -0.66
     effortlessly
    -0.65
    origin
    -0.65
     imported
    -0.64
    Origin
    -0.64
    esp
    -0.63
    chieve
    -0.63
    uably
    -0.62
    POSITIVE LOGITS
     adjourn
    1.22
     hearings
    0.97
     deliberations
    0.95
     tomorrow
    0.93
     arra
    0.92
     recess
    0.90
     courtroom
    0.90
     Thurs
    0.89
    istrate
    0.88
     mediation
    0.88
    Activations Density 0.222%

    No Known Activations