© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports news and analysis

    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
    330
    +0.10
    0.5%
    630
    +0.10
    0.4%
    188
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.10
    0.03
    70
    +0.10
    0.06
    665
    +0.09
    0.06
    Negative Logits
    conn
    -0.68
    usercontent
    -0.67
    folk
    -0.65
    thing
    -0.65
    riv
    -0.63
    lords
    -0.63
    External
    -0.62
    FactoryReloaded
    -0.61
    Ye
    -0.61
     sooner
    -0.59
    POSITIVE LOGITS
    hirt
    0.81
    ometimes
    0.76
    ilver
    0.67
     scathing
    0.63
     herself
    0.63
    creen
    0.63
     Shots
    0.62
    IGHTS
    0.62
    veland
    0.61
    hift
    0.61
    Activations Density 0.405%

    No Known Activations