Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43193
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to court rulings and campaign finance laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    100
    +0.12
    0.5%
    215
    +0.11
    0.5%
    668
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.12
    0.04
    398
    +0.11
    0.03
    215
    +0.10
    0.03
    Negative Logits
     Lonely
    -0.72
    ruary
    -0.72
     Slack
    -0.69
     [|
    -0.69
    ï¸ı
    -0.68
    Org
    -0.67
     tours
    -0.67
    mega
    -0.66
    nect
    -0.66
    cffffcc
    -0.65
    POSITIVE LOGITS
     defendant
    1.28
     unconstitutional
    1.24
     plaintiff
    1.19
     plaintiffs
    1.19
     appellant
    1.18
     constitutional
    1.17
     defendants
    1.16
     constitutionally
    1.11
     unlawfully
    1.10
     violated
    1.10
    Activations Density 0.336%

    No Known Activations