© 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 3072
    9. 8-RES_FS3072-JB
    11. 2960
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related language

    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
    187
    +0.10
    0.5%
    496
    +0.10
    0.5%
    558
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.10
    0.07
    495
    +0.10
    0.07
    558
    +0.10
    0.06
    Negative Logits
    tnc
    -0.76
     Chaser
    -0.73
    vier
    -0.73
    itte
    -0.67
    ¾
    -0.66
    pty
    -0.65
    uish
    -0.64
     Canaver
    -0.64
    arium
    -0.63
    ĸļ
    -0.62
    POSITIVE LOGITS
    lighting
    1.00
    landers
    0.93
     altitude
    0.91
    rise
    0.91
    fal
    0.90
     priced
    0.90
    lander
    0.87
     achie
    0.86
    rises
    0.86
     stakes
    0.85
    Activations Density 0.422%

    No Known Activations