© 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. 8697
    Prev
    Next
    INDEX
    Explanations

    references to a specific named individual

    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
    430
    +0.16
    0.7%
    339
    +0.12
    0.5%
    14
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.04
    339
    +0.12
    0.04
    162
    +0.09
    0.03
    Negative Logits
    nexus
    -0.69
     guiActiveUnfocused
    -0.65
     urgency
    -0.64
     forth
    -0.62
     mater
    -0.62
    interest
    -0.61
    Completed
    -0.60
     Angels
    -0.59
     lineback
    -0.58
    MQ
    -0.58
    POSITIVE LOGITS
     Trump
    1.30
    son
    1.11
     Donald
    1.02
    trump
    0.98
    Trump
    0.97
    Donald
    0.92
     Glover
    0.91
     Sterling
    0.90
     TRUMP
    0.84
     Duck
    0.84
    Activations Density 0.028%

    No Known Activations