© 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. 26635
    Prev
    Next
    INDEX
    Explanations

    occurrences of the year 2016

    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
    44
    +0.11
    0.5%
    317
    +0.10
    0.4%
    512
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.11
    0.04
    44
    +0.10
    0.03
    24
    +0.09
    0.03
    Negative Logits
    ificate
    -0.65
     cumbers
    -0.65
    FACE
    -0.63
     clipping
    -0.63
    iple
    -0.61
    stein
    -0.61
    peria
    -0.61
    angs
    -0.60
    imen
    -0.60
    Ń·
    -0.60
    POSITIVE LOGITS
    20439
    1.09
    bleacher
    0.81
    å¹
    0.74
    âĢ²
    0.72
     onwards
    0.72
    ivari
    0.69
    riots
    0.69
    riot
    0.67
     Olympics
    0.66
    âĢ³
    0.66
    Activations Density 0.038%

    No Known Activations