© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and legal proceedings

    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
    121
    +0.14
    0.6%
    459
    +0.13
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.07
    121
    +0.13
    0.05
    224
    +0.11
    0.05
    Negative Logits
    optim
    -0.84
     optim
    -0.80
    phies
    -0.77
     nostalg
    -0.73
    alg
    -0.72
     Remastered
    -0.70
    rowth
    -0.69
    ãĥ´
    -0.69
     Glac
    -0.68
    1080
    -0.68
    POSITIVE LOGITS
     sentenced
    1.40
     convicted
    1.39
     pleaded
    1.36
     arrested
    1.36
     defendants
    1.34
     unlawfully
    1.29
     accused
    1.26
     criminally
    1.26
     arra
    1.25
     prosecuted
    1.25
    Activations Density 0.398%

    No Known Activations