© 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. 26621
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms associated with characters or entities

    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
    526
    +0.15
    0.7%
    421
    +0.10
    0.5%
    211
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.15
    0.01
    565
    +0.10
    0.01
    478
    +0.10
    0.01
    Negative Logits
    senal
    -0.86
     Blueprint
    -0.71
    aeda
    -0.69
     deviations
    -0.68
    Reloaded
    -0.64
     Transparency
    -0.64
    inately
    -0.64
     body
    -0.61
    nces
    -0.60
     principals
    -0.60
    POSITIVE LOGITS
    ipe
    1.05
    ipeg
    1.05
    liness
    0.93
    borough
    0.90
     Mandela
    0.88
    ifest
    0.83
    emon
    0.83
    lette
    0.83
    ijah
    0.82
    ners
    0.82
    Activations Density 0.006%

    No Known Activations