© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 42999
    Prev
    Next
    INDEX
    Explanations

    periods and their frequencies of use in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.23
    1.1%
    640
    +0.16
    0.7%
    87
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.03
    464
    +0.16
    0.02
    284
    +0.11
    0.02
    Negative Logits
    enegger
    -0.76
     grounding
    -0.72
     withd
    -0.72
     behavi
    -0.69
     Vaugh
    -0.69
     conclud
    -0.68
     undermin
    -0.62
     agre
    -0.60
     thous
    -0.59
     casts
    -0.58
    POSITIVE LOGITS
    facebook
    0.99
    jpg
    0.95
    imgur
    0.95
    twitter
    0.93
    central
    0.92
    assetsadobe
    0.91
    htm
    0.91
    github
    0.88
    title
    0.88
    html
    0.88
    Activations Density 0.040%

    No Known Activations