© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10442
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or strategies that are characterized by assertiveness or dominance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    247
    +0.15
    0.7%
    447
    +0.12
    0.6%
    271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.15
    0.04
    247
    +0.12
    0.03
    288
    +0.12
    0.04
    Negative Logits
    ĸļ
    -0.89
    psons
    -0.83
    owship
    -0.79
    obyl
    -0.77
     Alive
    -0.74
    bel
    -0.72
    frey
    -0.71
    ãĤ´ãĥ³
    -0.70
    Vert
    -0.70
    FORE
    -0.70
    POSITIVE LOGITS
     behavior
    0.97
     aggressive
    0.97
     aggress
    0.96
     aggression
    0.94
     behaviour
    0.94
     behav
    0.92
     tendencies
    0.92
     toward
    0.92
     tactics
    0.90
     maneuvers
    0.87
    Activations Density 0.171%

    No Known Activations