© 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. 10-RES_POST_32K-OAI
    11. 26281
    Prev
    Next
    INDEX
    Explanations

    language associated with harmful or offensive content, including hate speech and threats

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    374
    +0.12
    0.6%
    755
    +0.10
    0.5%
    631
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.02
    284
    +0.10
    0.02
    125
    +0.09
    0.02
    Negative Logits
    ourses
    -0.88
    reb
    -0.67
    urized
    -0.65
    ilateral
    -0.65
    amorph
    -0.65
    olin
    -0.65
    ategory
    -0.64
    ikan
    -0.64
    MpServer
    -0.63
    axter
    -0.63
    POSITIVE LOGITS
    yright
    0.68
     sd
    0.64
     domain
    0.63
     php
    0.60
     messenger
    0.60
    ping
    0.58
     judgement
    0.58
     cliff
    0.58
     cliché
    0.58
     slowdown
    0.57
    Activations Density 0.281%

    No Known Activations