© 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. 8717
    Prev
    Next
    INDEX
    Explanations

    biographical information about historical figures or characters

    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
    11
    +0.11
    0.6%
    459
    +0.10
    0.5%
    762
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.02
    756
    +0.10
    -0.04
    283
    +0.10
    0.01
    Negative Logits
     LCS
    -0.86
     Marketplace
    -0.83
     2017
    -0.77
     Playoffs
    -0.76
    2017
    -0.76
     NETWORK
    -0.74
     Timeline
    -0.70
    odcast
    -0.70
     cybersecurity
    -0.69
     2018
    -0.69
    POSITIVE LOGITS
     convent
    0.81
     himself
    0.81
     arist
    0.80
     pious
    0.80
     trousers
    0.79
     piety
    0.76
     peasant
    0.76
     opium
    0.72
     herself
    0.72
     poet
    0.71
    Activations Density 1.612%

    No Known Activations