© 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. 28935
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries and body parts

    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
    219
    +0.11
    0.5%
    374
    +0.11
    0.5%
    274
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.04
    678
    +0.11
    0.04
    393
    +0.11
    0.05
    Negative Logits
     Dealer
    -0.80
    ezvous
    -0.77
    ILE
    -0.77
    DragonMagazine
    -0.76
     guiActiveUn
    -0.74
    soDeliveryDate
    -0.71
     Volunte
    -0.71
     Administ
    -0.70
    arcity
    -0.68
     WARN
    -0.67
    POSITIVE LOGITS
     legs
    1.74
     shoulders
    1.70
     thighs
    1.69
     knees
    1.69
     wrists
    1.68
     ankles
    1.67
     torso
    1.65
     abdomen
    1.63
     lungs
    1.61
     genitals
    1.60
    Activations Density 0.419%

    No Known Activations