© 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. 5946
    Prev
    Next
    INDEX
    Explanations

    phrases about books and possibly historical events

    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
    36
    +0.25
    1.2%
    481
    +0.20
    1.0%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.25
    0.18
    250
    +0.20
    0.09
    263
    +0.14
    0.08
    Negative Logits
    Contents
    -0.88
    alties
    -0.84
    eyes
    -0.83
    SIGN
    -0.78
    marks
    -0.73
    Hon
    -0.72
    pees
    -0.72
     knows
    -0.71
    Own
    -0.71
    apps
    -0.69
    POSITIVE LOGITS
     glimpse
    1.05
     bunch
    1.04
     mysterious
    1.02
     handful
    1.02
     snippet
    0.98
     strange
    0.97
     woman
    0.97
     guy
    0.97
     lot
    0.97
     couple
    0.96
    Activations Density 0.480%

    No Known Activations