© 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. 8-RES_POST_32K-OAI
    11. 6170
    Prev
    Next
    INDEX
    Explanations

    ethnic identifiers and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    302
    +0.13
    0.6%
    373
    +0.12
    0.6%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.01
    289
    +0.12
    0.00
    302
    +0.12
    0.01
    Negative Logits
    INGTON
    -0.82
    lessly
    -0.71
    atche
    -0.67
    mington
    -0.66
    aceous
    -0.66
     Huntington
    -0.64
    yip
    -0.64
     chronically
    -0.64
    aterasu
    -0.63
    merce
    -0.63
    POSITIVE LOGITS
    İ
    1.09
    ãĥĥãĥĪ
    1.09
    ãĥĥ
    1.06
    ãĥ¼
    1.06
    ãĥ¼ãĥ
    1.03
    ãĥ³
    1.00
    ãĤ¹ãĥĪ
    0.98
    ļ
    0.98
    ãĥĥãĤ¯
    0.97
    ãĤ¦
    0.95
    Activations Density 0.017%

    No Known Activations