© 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 49152
    9. 8-RES_FS49152-JB
    11. 37443
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing agreements

    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
    459
    +0.12
    0.6%
    508
    +0.12
    0.6%
    10
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.12
    0.01
    524
    +0.12
    0.01
    10
    +0.11
    0.01
    Negative Logits
    ilon
    -1.01
    dain
    -0.85
     Lans
    -0.82
    bra
    -0.77
    akia
    -0.75
    sonian
    -0.75
    te
    -0.74
    gres
    -0.72
    ilus
    -0.72
    usalem
    -0.72
    POSITIVE LOGITS
     licenses
    1.02
     licensing
    0.99
     fees
    0.95
     agreements
    0.94
     extensions
    0.88
     licences
    0.88
     royalties
    0.86
     approvals
    0.86
     infringement
    0.83
     compliance
    0.82
    Activations Density 0.011%

    No Known Activations