© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7417
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and events, particularly controversial statements/actions

    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
    373
    +0.20
    1.0%
    199
    +0.10
    0.5%
    335
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.20
    -0.01
    284
    +0.10
    0.04
    659
    +0.09
    0.04
    Negative Logits
    hammer
    -0.63
    ascript
    -0.62
     Grayson
    -0.58
     Pry
    -0.58
    drivers
    -0.58
    killers
    -0.57
    finder
    -0.56
     Norton
    -0.55
    bley
    -0.55
    finger
    -0.53
    POSITIVE LOGITS
    zeb
    0.86
    asca
    0.84
    uku
    0.82
    uchi
    0.78
    ondo
    0.78
    asa
    0.77
    osa
    0.75
    aru
    0.74
    arte
    0.74
    oga
    0.73
    Activations Density 0.106%

    No Known Activations