© 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 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. 29042
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to racial and ethnic demographics

    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
    125
    +0.09
    0.4%
    368
    +0.09
    0.4%
    14
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.09
    0.10
    255
    +0.09
    0.09
    439
    +0.09
    0.07
    Negative Logits
    awar
    -0.87
    ERG
    -0.82
    orage
    -0.76
    ERC
    -0.76
    ebted
    -0.75
    pload
    -0.74
    mosp
    -0.73
    soDeliveryDate
    -0.73
    RFC
    -0.73
    EMS
    -0.71
    POSITIVE LOGITS
     Discrimination
    0.99
     stereotyp
    0.92
     ancestry
    0.88
     discrimination
    0.87
     ancest
    0.86
     disparities
    0.85
     stereotypes
    0.84
     Gap
    0.84
     chromosomes
    0.83
     distinctions
    0.83
    Activations Density 0.913%

    No Known Activations