© 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. 42931
    Prev
    Next
    INDEX
    Explanations

    words related to organization or arrangement

    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
    349
    +0.10
    0.5%
    653
    +0.10
    0.5%
    445
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.02
    70
    +0.10
    0.02
    421
    +0.10
    0.02
    Negative Logits
    void
    -0.74
    assic
    -0.70
    aghd
    -0.68
    é¾įå
    -0.67
    hani
    -0.66
    utations
    -0.65
    onian
    -0.64
     burd
    -0.64
    wr
    -0.64
    Laughs
    -0.62
    POSITIVE LOGITS
     meetings
    0.93
     trips
    0.86
     consultations
    0.85
     screenings
    0.80
     lia
    0.80
     conferences
    0.78
    eer
    0.77
    eers
    0.76
     weddings
    0.74
     dinners
    0.74
    Activations Density 0.056%

    No Known Activations