© 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. 28868
    Prev
    Next
    INDEX
    Explanations

    references to significant events involving public figures or scandals

    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
    362
    +0.14
    0.7%
    161
    +0.12
    0.5%
    426
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.07
    608
    +0.12
    0.06
    161
    +0.10
    0.04
    Negative Logits
    ItemTracker
    -0.91
    istries
    -0.77
    pmwiki
    -0.73
    Rated
    -0.73
    WAYS
    -0.72
    terness
    -0.72
    vor
    -0.71
    ©¶æ¥µ
    -0.70
     proble
    -0.70
    advertising
    -0.69
    POSITIVE LOGITS
     naked
    1.07
     smiling
    1.03
     flowers
    0.94
     grinning
    0.88
    tnc
    0.87
     bearded
    0.87
     bruised
    0.83
     him
    0.81
     breasts
    0.77
     bare
    0.77
    Activations Density 0.527%

    No Known Activations