© 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 24576
    9. 8-RES_FS24576-JB
    11. 12503
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to the Little Rock area

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    352
    +0.10
    0.5%
    669
    +0.10
    0.5%
    666
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.10
    0.01
    482
    +0.10
    0.01
    666
    +0.10
    0.01
    Negative Logits
    inates
    -0.75
    ically
    -0.73
    iership
    -0.71
    atically
    -0.70
    EMENT
    -0.69
    ICA
    -0.68
    ickr
    -0.68
    ICAL
    -0.67
    icular
    -0.67
    ICAN
    -0.66
    POSITIVE LOGITS
    finger
    1.02
    woods
    0.89
    john
    0.85
     Havana
    0.81
    Brother
    0.81
     Mermaid
    0.81
     Debbie
    0.79
    wood
    0.79
    backer
    0.78
     Beaver
    0.77
    Activations Density 0.008%

    No Known Activations