© 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 12288
    9. 8-RES_FS12288-JB
    11. 1313
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.14
    0.6%
    160
    +0.11
    0.5%
    650
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.14
    0.09
    675
    +0.11
    0.08
    314
    +0.10
    0.03
    Negative Logits
     fert
    -0.65
     Mush
    -0.63
     Drawn
    -0.63
     leaps
    -0.62
     Rica
    -0.60
     mates
    -0.59
     vulner
    -0.58
     QC
    -0.58
     Carth
    -0.57
     sacrific
    -0.57
    POSITIVE LOGITS
    same
    1.20
    iest
    0.93
    ultimate
    0.91
    majority
    0.88
    original
    0.85
    ottest
    0.84
    osphere
    0.84
    venth
    0.82
    own
    0.81
    swer
    0.81
    Activations Density 0.312%

    No Known Activations