© 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. 18717
    Prev
    Next
    INDEX
    Explanations

    names or specific terms that appear in various contexts, potentially related to people, places, or 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
    373
    +0.18
    0.8%
    70
    +0.10
    0.4%
    543
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.18
    -0.01
    232
    +0.10
    0.04
    379
    +0.09
    0.03
    Negative Logits
    ħĭ
    -0.80
    ĸļ
    -0.72
    ACTED
    -0.72
     enactment
    -0.67
     exception
    -0.67
    ĪĴ
    -0.63
     caucuses
    -0.62
     consistency
    -0.62
     scrut
    -0.61
     depreciation
    -0.59
    POSITIVE LOGITS
    raltar
    0.93
    apon
    0.92
    onz
    0.91
    anan
    0.87
    reau
    0.86
    ierrez
    0.85
    illion
    0.85
    ppe
    0.84
    alez
    0.83
    apons
    0.82
    Activations Density 0.072%

    No Known Activations