© 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. 29173
    Prev
    Next
    INDEX
    Explanations

    political references and allegations related to prominent 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
    365
    +0.11
    0.5%
    389
    +0.09
    0.4%
    321
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.11
    1.00
    447
    +0.09
    0.97
    64
    +0.09
    -0.01
    Negative Logits
    SPONSORED
    -0.87
    Berry
    -0.85
    ONEY
    -0.82
    OWN
    -0.78
     AVG
    -0.75
    Ãĥ
    -0.70
    EGA
    -0.69
    DEF
    -0.69
    NetMessage
    -0.68
     Mali
    -0.68
    POSITIVE LOGITS
    ©¶æ
    0.82
     occas
    0.82
     proport
    0.79
    ¿½
    0.74
     rul
    0.73
    ntil
    0.72
     charism
    0.71
    ĪĴ
    0.70
     millenn
    0.70
    ŃĶ
    0.68
    Activations Density 2.496%

    No Known Activations