© 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 EvalsExportsinterp-engineNEWAPI 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. 28091
    Prev
    Next
    INDEX
    Explanations

    structural elements and keywords related to programming, particularly class and function definitions

    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
    337
    +0.13
    0.6%
    373
    +0.13
    0.6%
    81
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.09
    745
    +0.13
    -0.00
    755
    +0.10
    0.03
    Negative Logits
    zsche
    -0.86
    =/
    -0.74
    anthrop
    -0.73
     (>
    -0.70
    olina
    -0.68
    arians
    -0.68
     concess
    -0.67
     ISBN
    -0.66
    ="/
    -0.66
    anguage
    -0.66
    POSITIVE LOGITS
    catch
    0.95
    public
    0.90
    });
    0.89
    NetMessage
    0.84
     });
    0.82
    protected
    0.78
    private
    0.76
    void
    0.75
    ////////
    0.74
    Conclusion
    0.74
    Activations Density 0.916%

    No Known Activations