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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25694
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their positions

    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
    164
    +0.10
    0.5%
    12
    +0.10
    0.5%
    81
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.10
    0.04
    350
    +0.10
    0.03
    717
    +0.10
    0.02
    Negative Logits
    thood
    -0.80
     rave
    -0.73
    ãĥ¥
    -0.71
    mable
    -0.68
    tics
    -0.67
     scouts
    -0.64
     reproduction
    -0.63
     Comput
    -0.63
     tattoos
    -0.62
    books
    -0.62
    POSITIVE LOGITS
     Democrat
    1.17
    Republican
    1.10
     Republican
    1.05
    osponsors
    1.01
    Senate
    1.00
     Jr
    1.00
    ospons
    0.98
     Democratic
    0.96
     Senate
    0.95
     bipartisan
    0.93
    Activations Density 0.070%

    No Known Activations