© 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. 19842
    Prev
    Next
    INDEX
    Explanations

    topics related to political news, government activities, and ideological debates

    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
    358
    +0.11
    0.5%
    201
    +0.10
    0.4%
    285
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.11
    0.03
    201
    +0.10
    0.02
    590
    +0.09
    0.02
    Negative Logits
    inka
    -0.67
     hour
    -0.62
     Fairfax
    -0.62
    wives
    -0.62
     Advocate
    -0.60
    tein
    -0.60
     age
    -0.60
    Age
    -0.59
     Lords
    -0.59
     shadow
    -0.58
    POSITIVE LOGITS
    eter
    1.45
    .,
    1.36
    etc
    1.26
    .?
    1.25
    .;
    1.12
    .).
    1.11
    .—
    1.06
    .),
    1.04
    .,"
    1.01
    .:
    1.00
    Activations Density 0.014%

    No Known Activations