© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29685
    Prev
    Next
    INDEX
    Explanations

    topics related to societal issues and discrimination, particularly concerning Christians and the LGBTQ+ community

    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
    308
    +0.11
    0.5%
    438
    +0.10
    0.5%
    58
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.13
    759
    +0.10
    0.09
    51
    +0.10
    0.11
    Negative Logits
     caut
    -0.82
    tein
    -0.79
    inse
    -0.70
    iago
    -0.69
     corrid
    -0.67
     luggage
    -0.66
     smugg
    -0.65
     confir
    -0.65
     Inventory
    -0.65
     Vent
    -0.64
    POSITIVE LOGITS
     today
    1.09
    politics
    0.81
    needs
    0.77
     revolving
    0.75
     toward
    0.72
    today
    0.72
    geist
    0.70
     writ
    0.69
     polarized
    0.69
    iven
    0.69
    Activations Density 1.738%

    No Known Activations