© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    sentences ending with punctuation marks

    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
    373
    +0.25
    1.1%
    314
    +0.12
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.25
    0.28
    145
    +0.12
    0.21
    640
    +0.11
    0.20
    Negative Logits
    oaded
    -0.64
     levers
    -0.57
    ividual
    -0.55
     trouble
    -0.53
     cov
    -0.53
     destro
    -0.52
    ruciating
    -0.52
     thous
    -0.52
    ensibly
    -0.52
     shorthand
    -0.51
    POSITIVE LOGITS
    <|endoftext|>
    1.03
    ↵
    1.00
    ↵Âł
    0.95
     Lastly
    0.94
    SPONSORED
    0.85
    ↵↵
    0.83
    Conclusion
    0.81
    ________________________________
    0.80
    Lastly
    0.80
    ================================================================
    0.79
    Activations Density 1.770%

    No Known Activations