© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 31463
    Prev
    Next
    INDEX
    Explanations

    terms related to aggressive behavior or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    247
    +0.17
    0.8%
    387
    +0.12
    0.6%
    271
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.05
    247
    +0.12
    0.04
    271
    +0.11
    0.03
    Negative Logits
    ĸļ
    -0.85
    enfranch
    -0.83
    psons
    -0.78
    ãĤ´ãĥ³
    -0.75
    aston
    -0.71
    algia
    -0.71
     Siem
    -0.71
    frey
    -0.68
    ocument
    -0.67
    ichen
    -0.65
    POSITIVE LOGITS
     posture
    0.91
     toward
    0.91
    ressive
    0.84
     towards
    0.84
     aggressively
    0.78
     behavior
    0.75
     tendencies
    0.75
     stance
    0.75
     behaviour
    0.73
     aggression
    0.73
    Activations Density 0.274%

    No Known Activations