© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 5915
    Prev
    Next
    INDEX
    Explanations

    subscription-related phrases and user actions in newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    211
    +0.10
    0.5%
    760
    +0.10
    0.4%
    659
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.10
    0.05
    373
    +0.10
    -0.01
    257
    +0.09
    0.05
    Negative Logits
    hee
    -0.64
    aimon
    -0.61
     Hearth
    -0.60
    iage
    -0.57
     Rational
    -0.57
     Holo
    -0.57
     Catalyst
    -0.56
     GAME
    -0.55
     Beaver
    -0.55
     Esther
    -0.54
    POSITIVE LOGITS
    interstitial
    0.82
     });
    0.78
     newsletters
    0.77
    ]+
    0.72
     newsletter
    0.72
    ]);
    0.70
     Newsletter
    0.69
    à¤
    0.69
    Phones
    0.67
    ··
    0.66
    Activations Density 0.122%

    No Known Activations