© 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 EvalsExportsinterp-engineNEWAPI 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. 45440
    Prev
    Next
    INDEX
    Explanations

    references to benefits in various contexts

    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
    288
    +0.16
    0.7%
    314
    +0.12
    0.5%
    97
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.16
    0.01
    285
    +0.12
    0.01
    712
    +0.11
    0.01
    Negative Logits
     Rim
    -0.73
    ilk
    -0.70
    hn
    -0.70
    vez
    -0.66
     Sturgeon
    -0.65
     Monstrous
    -0.64
    body
    -0.64
     Dynam
    -0.63
    wed
    -0.63
     fried
    -0.62
    POSITIVE LOGITS
    ocratic
    0.90
    ochond
    0.89
     claimants
    0.86
    lication
    0.83
    farious
    0.83
    benefit
    0.83
     conferred
    0.81
    iciary
    0.81
    uary
    0.80
    onies
    0.79
    Activations Density 0.009%

    No Known Activations