© 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. 31171
    Prev
    Next
    INDEX
    Explanations

    references to individual political figures

    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
    688
    +0.11
    0.5%
    277
    +0.10
    0.5%
    60
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.11
    0.06
    417
    +0.10
    0.04
    69
    +0.10
    0.05
    Negative Logits
     Sultan
    -1.11
     Yaz
    -1.07
     Saddam
    -0.98
     Baghdad
    -0.96
    merga
    -0.96
    Iraq
    -0.95
     Franks
    -0.94
     Armen
    -0.94
     Kurd
    -0.93
     Iraqi
    -0.93
    POSITIVE LOGITS
     Sanders
    2.15
    Sanders
    2.00
    Bernie
    1.80
     Vermont
    1.78
     Bernie
    1.74
     Burlington
    1.66
     socialist
    1.26
     socialists
    1.25
     socialism
    1.19
     Socialist
    1.06
    Activations Density 2.408%

    No Known Activations