© 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. 28610
    Prev
    Next
    INDEX
    Explanations

    references to political figures or events

    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
    74
    +0.14
    0.6%
    756
    +0.13
    0.6%
    750
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.14
    0.02
    479
    +0.13
    0.01
    543
    +0.13
    0.05
    Negative Logits
    Egypt
    -1.25
    Tesla
    -1.15
     Mubarak
    -1.11
     Egyptians
    -1.09
     Tesla
    -1.09
     Bezos
    -1.03
     Egyptian
    -1.03
     Morsi
    -1.02
     Egypt
    -1.01
     Memphis
    -0.98
    POSITIVE LOGITS
     Irish
    1.89
    Irish
    1.87
    Ireland
    1.78
     Dublin
    1.73
     Ireland
    1.68
     Cork
    1.68
     Ulster
    1.61
     Sinn
    1.43
     Gael
    1.42
     TDs
    1.40
    Activations Density 4.406%

    No Known Activations