© 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. 31542
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    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
    722
    +0.10
    0.5%
    426
    +0.09
    0.4%
    235
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.10
    0.03
    683
    +0.09
    0.03
    737
    +0.08
    0.03
    Negative Logits
    ãĥ¼ãĥĨ
    -0.69
    ModLoader
    -0.69
    conservancy
    -0.65
    die
    -0.64
    cially
    -0.62
    pause
    -0.61
    uct
    -0.59
    nesday
    -0.59
    interstitial
    -0.59
    versely
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.11
     whats
    0.91
     what
    0.83
     why
    0.79
    what
    0.78
     how
    0.76
     damn
    0.71
     squat
    0.67
    how
    0.67
     WHAT
    0.66
    Activations Density 0.144%

    No Known Activations