© 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. 26933
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific people, places, or organizations

    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
    559
    +0.12
    0.5%
    289
    +0.11
    0.5%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    503
    +0.11
    0.01
    232
    +0.09
    0.01
    Negative Logits
    hower
    -0.86
    terday
    -0.72
    ffen
    -0.68
    croft
    -0.64
     roy
    -0.62
    BIP
    -0.62
     Mub
    -0.61
    enegger
    -0.61
     Franch
    -0.58
    ÄŁ
    -0.57
    POSITIVE LOGITS
    ı
    1.50
    ģ
    1.43
    Ħ
    1.43
    Ī
    1.43
    į
    1.39
    ĩ
    1.35
    ħ
    1.33
    Ģ
    1.31
    ĥ
    1.25
    ļ
    1.18
    Activations Density 0.027%

    No Known Activations