© 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. 30493
    Prev
    Next
    INDEX
    Explanations

    geographic locations and names related to political entities or representatives

    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
    642
    +0.12
    0.5%
    693
    +0.10
    0.4%
    230
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.05
    659
    +0.10
    0.04
    380
    +0.09
    0.03
    Negative Logits
     weap
    -0.77
     deduct
    -0.74
     deeds
    -0.72
     dex
    -0.71
     signings
    -0.69
     disse
    -0.66
     fingerprints
    -0.65
     evils
    -0.65
     impe
    -0.65
     substit
    -0.64
    POSITIVE LOGITS
    )|
    1.15
     Region
    1.04
    region
    0.99
     âĵĺ
    0.91
    )",
    0.91
    ãĤ¼ãĤ¦ãĤ¹
    0.90
     Peninsula
    0.89
    fecture
    0.88
    \",
    0.88
     [|
    0.87
    Activations Density 0.165%

    No Known Activations