© 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. 31156
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    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
    430
    +0.15
    0.7%
    535
    +0.09
    0.4%
    442
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.15
    0.04
    297
    +0.09
    0.04
    430
    +0.09
    0.04
    Negative Logits
    ¶
    -0.65
    inctions
    -0.63
     constitu
    -0.57
     pedigree
    -0.56
    chy
    -0.55
    isphere
    -0.54
     weave
    -0.54
    RW
    -0.54
    ļéĨĴ
    -0.54
     curl
    -0.53
    POSITIVE LOGITS
     2017
    1.83
     2015
    1.77
     2016
    1.77
     2014
    1.76
     2013
    1.74
     2018
    1.69
     2012
    1.69
     2011
    1.63
    2017
    1.59
     2010
    1.56
    Activations Density 0.147%

    No Known Activations