© 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. 19554
    Prev
    Next
    INDEX
    Explanations

    photographs or images to highlight or focus on

    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
    +0.20
    1.0%
    746
    +0.09
    0.4%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.20
    -0.00
    106
    +0.09
    0.01
    491
    +0.09
    0.01
    Negative Logits
    stood
    -0.63
    angers
    -0.62
    anger
    -0.62
     upt
    -0.61
    angering
    -0.61
     cardinal
    -0.60
     crowds
    -0.58
    fulness
    -0.58
    shall
    -0.58
    population
    -0.58
    POSITIVE LOGITS
    Enlarge
    0.93
    ONSORED
    0.92
     WATCHED
    0.89
    UTERS
    0.82
     toggle
    0.76
     caption
    0.76
     Flavoring
    0.73
     "$:/
    0.72
    hran
    0.71
     Image
    0.70
    Activations Density 0.007%

    No Known Activations