© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 43027
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate parts of a system or structure

    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
    583
    +0.09
    0.4%
    657
    +0.09
    0.4%
    425
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.09
    0.03
    657
    +0.09
    0.03
    425
    +0.09
    0.02
    Negative Logits
    NL
    -0.71
    ername
    -0.70
    IRC
    -0.67
    çīĪ
    -0.65
    chester
    -0.64
    pless
    -0.63
    mount
    -0.63
    wcs
    -0.63
    è¦ļéĨĴ
    -0.62
    ãĤ°
    -0.62
    POSITIVE LOGITS
     play
    0.76
     computation
    0.73
    rontal
    0.72
     accomplishment
    0.71
     occurrence
    0.71
     expression
    0.70
     attainment
    0.67
     engagement
    0.67
     stature
    0.66
    inement
    0.66
    Activations Density 0.057%

    No Known Activations