© 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. 27961
    Prev
    Next
    INDEX
    Explanations

    geographical and political references related to regions and countries

    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
    519
    +0.09
    0.4%
    55
    +0.09
    0.4%
    530
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.09
    -0.02
    406
    +0.09
    0.09
    232
    +0.09
    0.09
    Negative Logits
     smoker
    -0.76
    ividual
    -0.67
    actionDate
    -0.66
     curve
    -0.66
     mathemat
    -0.66
     skelet
    -0.66
    displayText
    -0.65
    xual
    -0.65
     condom
    -0.65
     waiter
    -0.65
    POSITIVE LOGITS
     France
    1.53
     Italy
    1.53
     Spain
    1.51
     England
    1.48
     Europe
    1.47
     Germany
    1.47
     Poland
    1.46
     Arabia
    1.46
     Australia
    1.44
     Ireland
    1.43
    Activations Density 2.274%

    No Known Activations