© 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. 22229
    Prev
    Next
    INDEX
    Explanations

    parentheses and similar punctuation marks

    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
    640
    +0.21
    1.0%
    314
    +0.19
    0.9%
    480
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.21
    0.03
    314
    +0.19
    0.01
    640
    +0.17
    0.02
    Negative Logits
     nuts
    -0.77
    wagen
    -0.73
     piping
    -0.72
     appropri
    -0.71
     everyday
    -0.69
     gems
    -0.69
     arbitrarily
    -0.67
     discrim
    -0.67
     orchestr
    -0.66
     erect
    -0.66
    POSITIVE LOGITS
    Reuters
    1.21
    emphasis
    1.05
    Photo
    1.04
    credit
    1.02
    Thom
    1.01
    Courtesy
    1.00
    UTERS
    0.99
    CNN
    0.98
    â̦)
    0.96
    written
    0.96
    Activations Density 0.034%

    No Known Activations