© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18785
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions and rulings in court cases

    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
    631
    +0.12
    0.5%
    756
    +0.12
    0.5%
    80
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.12
    0.04
    631
    +0.12
    0.04
    654
    +0.11
    0.03
    Negative Logits
    ãĥĺ
    -0.79
    è¦ļéĨĴ
    -0.75
    abwe
    -0.70
    é¾
    -0.67
    plot
    -0.66
    OVA
    -0.65
    odan
    -0.65
    ãĤ±
    -0.65
     Addiction
    -0.64
    qv
    -0.64
    POSITIVE LOGITS
     unanimously
    0.94
     upholding
    0.92
     defendants
    0.87
     petitioner
    0.86
     sided
    0.83
     plaintiffs
    0.82
     cert
    0.82
     plaintiff
    0.82
     rejecting
    0.82
     defendant
    0.82
    Activations Density 0.153%

    No Known Activations