© 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. 28434
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their use in coding syntax

    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
    314
    +0.13
    0.6%
    99
    +0.10
    0.4%
    537
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.06
    700
    +0.10
    0.05
    678
    +0.09
    0.04
    Negative Logits
     Blackburn
    -0.83
     Sutherland
    -0.81
     Preston
    -0.76
     Tenn
    -0.75
     Watt
    -0.75
     Hastings
    -0.73
     Kashmir
    -0.70
     Gardens
    -0.70
     Moff
    -0.69
     Waterloo
    -0.67
    POSITIVE LOGITS
    ++;
    1.11
    ;}
    0.91
     //[
    0.90
    +=
    0.88
    float
    0.86
     /*
    0.85
    }}
    0.85
    while
    0.84
    };
    0.83
    }}}
    0.82
    Activations Density 0.273%

    No Known Activations