© 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. 27835
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers associated with technological or data-related contexts

    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
    493
    +0.10
    0.5%
    639
    +0.10
    0.4%
    736
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.10
    0.00
    674
    +0.10
    0.01
    76
    +0.10
    0.01
    Negative Logits
    selves
    -0.86
    ','
    -0.83
    /
    -0.77
    swick
    -0.73
    âĹ¼
    -0.72
    yss
    -0.72
    strous
    -0.72
    ãĢİ
    -0.72
    """
    -0.72
    FTWARE
    -0.71
    POSITIVE LOGITS
     Currency
    1.02
    isec
    0.70
    DN
    0.65
    cookie
    0.62
    erald
    0.61
    fx
    0.56
    ilon
    0.55
    lio
    0.54
    Eth
    0.54
    lav
    0.53
    Activations Density 0.034%

    No Known Activations