© 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. 29191
    Prev
    Next
    INDEX
    Explanations

    expressions related to political critique and controversy

    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
    373
    +0.14
    0.6%
    745
    +0.12
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.14
    0.08
    619
    +0.12
    0.07
    472
    +0.11
    0.03
    Negative Logits
     Died
    -0.72
    shit
    -0.72
    fuck
    -0.71
    upon
    -0.69
     LIFE
    -0.66
     yea
    -0.65
     (/
    -0.65
     FUCK
    -0.65
    HAHA
    -0.64
     amaz
    -0.63
    POSITIVE LOGITS
     unfairly
    1.28
     too
    1.04
    too
    0.98
     undue
    0.97
     overly
    0.94
     overshadow
    0.90
     inappropriately
    0.89
     unnecessarily
    0.89
     politic
    0.88
     improperly
    0.87
    Activations Density 2.635%

    No Known Activations