© 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. 41510
    Prev
    Next
    INDEX
    Explanations

    action verbs related to achievements and progress

    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
    309
    +0.10
    0.4%
    722
    +0.10
    0.4%
    224
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.06
    123
    +0.10
    0.04
    641
    +0.09
    0.04
    Negative Logits
    pmwiki
    -0.69
    riad
    -0.65
     Subtle
    -0.63
    wordpress
    -0.63
     anecd
    -0.60
    ItemTracker
    -0.60
    oggles
    -0.59
     modeled
    -0.59
    catentry
    -0.59
    ãģ®
    -0.58
    POSITIVE LOGITS
    ().
    0.74
     purposes
    0.72
    agate
    0.67
    equality
    0.66
    inka
    0.65
    ativity
    0.65
     Ratio
    0.65
    uate
    0.64
    maximum
    0.62
    auna
    0.60
    Activations Density 0.213%

    No Known Activations