© 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. 26209
    Prev
    Next
    INDEX
    Explanations

    terms related to offensive and discriminatory speech or actions

    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
    720
    +0.11
    0.5%
    412
    +0.11
    0.5%
    55
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.11
    0.07
    351
    +0.11
    0.05
    103
    +0.10
    0.04
    Negative Logits
     Attribution
    -0.71
    lear
    -0.69
    iets
    -0.68
    asury
    -0.67
    aea
    -0.67
    amsung
    -0.67
    pection
    -0.66
    rians
    -0.66
    obos
    -0.65
     nuances
    -0.64
    POSITIVE LOGITS
     homophobic
    1.17
     sexist
    1.09
     misogyn
    1.08
     degrading
    1.05
     hateful
    1.04
     discriminatory
    1.01
     xen
    1.00
     immoral
    0.94
     abusive
    0.94
     bigot
    0.94
    Activations Density 0.752%

    No Known Activations