© 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. 31070
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and character symbols, as well as the presence of repeated or common phrases

    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
    357
    +0.13
    0.6%
    683
    +0.10
    0.5%
    99
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.00
    659
    +0.10
    0.03
    406
    +0.10
    0.03
    Negative Logits
    alore
    -0.88
    yip
    -0.79
     Glacier
    -0.69
     Tart
    -0.65
    tu
    -0.64
     simultane
    -0.64
    20439
    -0.63
    )=(
    -0.63
    kef
    -0.62
    anwhile
    -0.62
    POSITIVE LOGITS
    án
    1.04
    aan
    1.03
    an
    1.02
    anic
    0.98
    rics
    0.78
    anes
    0.72
    ã
    0.72
    â
    0.71
    ean
    0.71
    ans
    0.70
    Activations Density 0.224%

    No Known Activations