© 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 EvalsExportsinterp-engineNEWAPI 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. 45433
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in the text

    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
    380
    +0.10
    0.5%
    542
    +0.09
    0.4%
    217
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.06
    720
    +0.09
    0.06
    546
    +0.09
    0.06
    Negative Logits
    zona
    -0.72
    ahime
    -0.69
    boro
    -0.67
     guiActiveUnfocused
    -0.66
    olves
    -0.64
    ../
    -0.64
    STATE
    -0.63
    thur
    -0.60
    types
    -0.59
    pleted
    -0.58
    POSITIVE LOGITS
     however
    1.48
     moreover
    1.33
     meanwhile
    1.28
     according
    1.14
     though
    1.09
     incidentally
    1.09
     alas
    1.08
     therefore
    1.02
     anyway
    0.97
     says
    0.95
    Activations Density 0.219%

    No Known Activations