© 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. 31260
    Prev
    Next
    INDEX
    Explanations

    mentions of prominent individuals or entities in a political context

    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
    373
    +0.16
    0.7%
    420
    +0.12
    0.6%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.16
    -0.01
    373
    +0.12
    -0.04
    365
    +0.11
    0.00
    Negative Logits
     externalToEVAOnly
    -0.71
    hower
    -0.67
     Citation
    -0.63
     Teach
    -0.61
    illac
    -0.60
    dfx
    -0.60
    Bloomberg
    -0.57
     Liver
    -0.57
     Cake
    -0.56
     Manip
    -0.55
    POSITIVE LOGITS
    en
    0.76
    advertising
    0.72
    isf
    0.69
    astical
    0.66
    atters
    0.64
    ©
    0.64
    za
    0.63
    ote
    0.62
    eworthy
    0.62
    astically
    0.61
    Activations Density 0.675%

    No Known Activations