© 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 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. 6406
    Prev
    Next
    INDEX
    Explanations

    words associated with tangible results or outcomes

    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
    408
    +0.15
    0.7%
    481
    +0.14
    0.6%
    187
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.15
    0.04
    428
    +0.14
    0.03
    288
    +0.10
    0.04
    Negative Logits
    cius
    -0.87
    asus
    -0.78
    ressor
    -0.75
    ammers
    -0.75
    ression
    -0.75
    conservancy
    -0.73
    ħ
    -0.72
    paces
    -0.72
    illard
    -0.71
    axter
    -0.71
    POSITIVE LOGITS
    izable
    1.05
     evidence
    1.01
     proof
    0.95
     measure
    0.92
     manifestation
    0.92
    isable
    0.91
     basis
    0.91
     evid
    0.88
     measurable
    0.88
     impossibility
    0.85
    Activations Density 0.119%

    No Known Activations