© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 9098
    Prev
    Next
    INDEX
    Explanations

    words related to offensive actions or combat scenarios

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.12
    0.5%
    756
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.03
    601
    +0.11
    0.02
    379
    +0.10
    0.03
    Negative Logits
    ãĤ©
    -0.81
    zl
    -0.81
    姫
    -0.74
    milo
    -0.73
    theless
    -0.68
    inder
    -0.64
     compr
    -0.62
     Seller
    -0.62
    YC
    -0.60
    mberg
    -0.57
    POSITIVE LOGITS
    ive
    0.92
    ivation
    0.89
    ivated
    0.80
    iveness
    0.79
    ivating
    0.73
     vector
    0.72
    oise
    0.72
    quit
    0.71
    ivist
    0.68
    OE
    0.68
    Activations Density 0.087%

    No Known Activations