© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10906
    Prev
    Next
    INDEX
    Explanations

    references to police operations or aggressive interventions

    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
    0.6%
    269
    +0.11
    0.5%
    489
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.12
    0.02
    460
    +0.11
    0.01
    288
    +0.11
    0.01
    Negative Logits
    DonaldTrump
    -0.66
    chell
    -0.63
     Leilan
    -0.62
    Ian
    -0.62
    Fed
    -0.61
    ansson
    -0.61
    éĸ
    -0.61
    milo
    -0.59
     Gork
    -0.58
    assetsadobe
    -0.58
    POSITIVE LOGITS
    ers
    0.91
     raid
    0.88
     raids
    0.85
    bing
    0.77
     raided
    0.76
     raiding
    0.76
    Raid
    0.75
    ishly
    0.74
    nard
    0.73
    iversary
    0.71
    Activations Density 0.025%

    No Known Activations