© 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 EvalsExportsinterp-engineNEWAPI 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. 17135
    Prev
    Next
    INDEX
    Explanations

    specific game-related terms and abilities associated with a strategic video game character

    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
    189
    +0.10
    0.5%
    732
    +0.10
    0.4%
    326
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.10
    0.03
    326
    +0.10
    0.02
    575
    +0.10
    0.03
    Negative Logits
     Indies
    -0.75
    isle
    -0.75
    llah
    -0.73
    lihood
    -0.71
     Lions
    -0.70
     Helsinki
    -0.68
     Kinn
    -0.68
    noon
    -0.67
    ardy
    -0.67
     Manz
    -0.67
    POSITIVE LOGITS
     cooldown
    1.20
     abilities
    1.05
     synerg
    0.95
    Cooldown
    0.94
     modifiers
    0.94
     modifier
    0.88
     combos
    0.88
     synergy
    0.88
     glyph
    0.85
     Cooldown
    0.85
    Activations Density 0.086%

    No Known Activations