© 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. 19835
    Prev
    Next
    INDEX
    Explanations

    phrases related to political support or stance

    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
    447
    +0.12
    0.5%
    143
    +0.11
    0.5%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.12
    0.03
    78
    +0.11
    0.03
    521
    +0.10
    0.02
    Negative Logits
    istical
    -0.82
    ptoms
    -0.81
     proble
    -0.75
     nerv
    -0.74
    ixtape
    -0.72
    vity
    -0.70
     teasp
    -0.70
    ÃŃa
    -0.70
    atonin
    -0.69
    iae
    -0.69
    POSITIVE LOGITS
     legalizing
    0.86
     abolition
    0.80
     independence
    0.80
     reelection
    0.80
     Supports
    0.76
     amnesty
    0.75
     electing
    0.74
     adoption
    0.74
     endorsing
    0.74
     Proposition
    0.73
    Activations Density 0.076%

    No Known Activations