© 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. 27918
    Prev
    Next
    INDEX
    Explanations

    phrases related to anti-Muslim sentiment and experiences of discrimination

    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
    246
    +0.12
    0.5%
    252
    +0.11
    0.5%
    294
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.12
    86
    +0.11
    0.10
    103
    +0.11
    0.09
    Negative Logits
     Mell
    -0.93
    iquid
    -0.84
     Hydro
    -0.83
    Hyd
    -0.83
    NetMessage
    -0.82
     Gorge
    -0.81
     Rhod
    -0.80
    natureconservancy
    -0.79
     Eli
    -0.79
     Storage
    -0.79
    POSITIVE LOGITS
     Muslims
    2.01
    Muslims
    1.97
     Muslim
    1.96
     Islam
    1.92
     mosques
    1.89
    Muslim
    1.86
    Islam
    1.75
     Sharia
    1.73
     mosque
    1.70
     Koran
    1.66
    Activations Density 6.032%

    No Known Activations