© 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 24576
    9. 8-RES_FS24576-JB
    11. 19663
    Prev
    Next
    INDEX
    Explanations

    countries and addresses

    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
    459
    +0.13
    0.6%
    67
    +0.11
    0.5%
    289
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.13
    0.07
    57
    +0.11
    0.05
    752
    +0.10
    0.06
    Negative Logits
    icer
    -0.74
    zik
    -0.70
    struct
    -0.70
    acl
    -0.69
    ashington
    -0.67
    claw
    -0.67
    ŃĶ
    -0.67
    msg
    -0.67
    oggle
    -0.66
    iazep
    -0.65
    POSITIVE LOGITS
     shores
    0.97
     Territories
    0.92
     Customers
    0.87
     markets
    0.84
     indie
    0.81
     localization
    0.80
     distributor
    0.80
     NTS
    0.80
    ESE
    0.77
     distributors
    0.77
    Activations Density 0.228%

    No Known Activations