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 6144
    5. 8-RES_FS6144-JB
    6. 4499
    Prev
    Next
    INDEX
    Explanations

    references to political figures or events, particularly focused on the actions or statements of President George W. Bush

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    711
    +0.12
    0.6%
    306
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.06
    284
    +0.11
    0.04
    350
    +0.09
    0.04
    Negative Logits
    liga
    -0.80
     heels
    -0.75
    eele
    -0.67
    vec
    -0.67
    gaard
    -0.64
    å
    -0.61
    cham
    -0.61
    dog
    -0.59
    ocre
    -0.59
    Ont
    -0.59
    POSITIVE LOGITS
     Abrams
    0.83
     Bush
    0.77
     Reagan
    0.73
    Bush
    0.68
     Roberts
    0.67
     Fitzgerald
    0.66
     McAuliffe
    0.66
     Gates
    0.64
     Romero
    0.64
     Faul
    0.61
    Activations Density 0.342%

    No Known Activations