© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22245
    Prev
    Next
    INDEX
    Explanations

    various forms of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    393
    +0.13
    0.6%
    176
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.13
    0.05
    176
    +0.11
    0.04
    530
    +0.10
    0.04
    Negative Logits
    usting
    -0.76
    ":"/
    -0.72
    usted
    -0.72
    ãĥ¼ãĤ¯
    -0.70
    imester
    -0.69
    entimes
    -0.67
    rising
    -0.66
    algia
    -0.66
    iculty
    -0.64
    iners
    -0.64
    POSITIVE LOGITS
     etc
    1.46
    etc
    0.93
     et
    0.85
     Moroc
    0.83
     Sod
    0.80
     Seat
    0.79
     Et
    0.76
     Izan
    0.75
     Lad
    0.75
     Mast
    0.75
    Activations Density 0.136%

    No Known Activations