© 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 49152
    9. 8-RES_FS49152-JB
    11. 45487
    Prev
    Next
    INDEX
    Explanations

    references to petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.13
    0.6%
    526
    +0.11
    0.5%
    31
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.13
    0.01
    31
    +0.11
    0.01
    253
    +0.10
    0.01
    Negative Logits
    lasses
    -0.88
    ectar
    -0.70
     Tune
    -0.65
    çīĪ
    -0.63
    orf
    -0.61
    quickShipAvailable
    -0.61
     Haram
    -0.61
    antle
    -0.60
    bane
    -0.60
    obyl
    -0.59
    POSITIVE LOGITS
     petitions
    0.99
     petition
    0.98
    ers
    0.91
    naires
    0.88
     filed
    0.85
    ing
    0.84
     Petition
    0.82
    aires
    0.82
    ingham
    0.81
     signatures
    0.79
    Activations Density 0.010%

    No Known Activations