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

    Neuronpedia

    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. 8193
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or situations

    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
    +0.15
    0.7%
    680
    +0.12
    0.5%
    659
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    562
    +0.15
    0.02
    393
    +0.12
    0.03
    306
    +0.10
    0.02
    Negative Logits
    orthy
    -0.98
    izons
    -0.86
    isons
    -0.85
    erate
    -0.85
    iar
    -0.81
    ield
    -0.81
    visor
    -0.80
    awi
    -0.79
    eri
    -0.78
    igible
    -0.77
    POSITIVE LOGITS
     pesky
    0.85
     infamous
    0.82
     famous
    0.78
     legendary
    0.78
     acron
    0.77
     commercials
    0.76
     dreaded
    0.74
     roller
    0.71
     last
    0.71
     LAST
    0.70
    Activations Density 0.175%

    No Known Activations