© 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. 9141
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and actions

    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
    218
    +0.14
    0.6%
    327
    +0.12
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.14
    0.05
    218
    +0.12
    0.04
    102
    +0.10
    0.05
    Negative Logits
     VIDEOS
    -0.96
     leases
    -0.78
     occurs
    -0.74
     patents
    -0.74
     births
    -0.73
     pregnancies
    -0.70
    metics
    -0.68
    onds
    -0.67
    opened
    -0.67
     PLUS
    -0.66
    POSITIVE LOGITS
     invincible
    0.95
     arrogant
    0.93
     traitor
    0.92
     savior
    0.91
     unbeat
    0.91
     hypocr
    0.90
     fearless
    0.88
     hero
    0.88
     ruthless
    0.86
     charismatic
    0.86
    Activations Density 0.276%

    No Known Activations