© 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. 6377
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and titles of characters and entities

    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
    710
    +0.11
    0.5%
    597
    +0.10
    0.5%
    36
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.04
    373
    +0.10
    -0.01
    466
    +0.10
    0.03
    Negative Logits
    nings
    -0.68
    âĹ¼
    -0.63
    cius
    -0.63
     Scand
    -0.62
    76561
    -0.60
    edi
    -0.59
    rious
    -0.59
     sidx
    -0.59
    mington
    -0.59
    EVA
    -0.59
    POSITIVE LOGITS
    ģĸ
    0.80
    ª
    0.76
    ĨĴ
    0.71
    ¢
    0.69
    £ı
    0.67
    ī
    0.66
     Dusk
    0.66
    ĺ
    0.66
     eleg
    0.66
    ¼
    0.66
    Activations Density 0.083%

    No Known Activations