© 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. 29870
    Prev
    Next
    INDEX
    Explanations

    references to specific demographic groups, particularly those related to ethnicity, religion, and social status

    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
    408
    +0.13
    0.6%
    219
    +0.10
    0.5%
    660
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.10
    752
    +0.10
    0.07
    132
    +0.10
    0.04
    Negative Logits
    bows
    -1.05
    ories
    -0.99
    estyles
    -0.96
    atories
    -0.95
    ologies
    -0.94
    laws
    -0.94
    ples
    -0.92
    brids
    -0.92
    renches
    -0.92
    ernels
    -0.92
    POSITIVE LOGITS
     who
    1.36
     whose
    1.17
     woman
    1.08
     named
    1.02
     teenager
    1.01
     businessman
    1.00
     whom
    0.99
     politician
    0.97
     traveler
    0.94
     citizen
    0.92
    Activations Density 0.768%

    No Known Activations