© 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. 464
    Prev
    Next
    INDEX
    Explanations

    mentions of television, networks, and shows

    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
    288
    +0.13
    0.6%
    741
    +0.12
    0.6%
    725
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.13
    0.04
    741
    +0.12
    0.03
    76
    +0.11
    0.03
    Negative Logits
    cius
    -0.69
    urat
    -0.69
    ta
    -0.65
    etsy
    -0.64
    arcity
    -0.64
    uth
    -0.64
    aido
    -0.63
    adow
    -0.63
    upid
    -0.63
     descent
    -0.63
    POSITIVE LOGITS
     broadcasts
    1.20
     commercials
    1.10
     broadcasting
    1.06
     broadcasters
    1.06
    levision
    1.04
     advertisements
    0.95
     broadcast
    0.93
     television
    0.92
     broadcaster
    0.92
     productions
    0.91
    Activations Density 0.102%

    No Known Activations