© 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. 28004
    Prev
    Next
    INDEX
    Explanations

    references to legal sections and documents

    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
    408
    +0.10
    0.5%
    564
    +0.10
    0.4%
    501
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.10
    0.01
    373
    +0.10
    -0.01
    701
    +0.10
    0.01
    Negative Logits
    orno
    -0.84
    udo
    -0.81
    ngth
    -0.81
    cius
    -0.79
    erv
    -0.76
    heit
    -0.75
    mble
    -0.74
    DEF
    -0.74
    ktop
    -0.71
    artisan
    -0.70
    POSITIVE LOGITS
     1
    0.72
    BuyableInstoreAndOnline
    0.71
     sleeves
    0.62
     2
    0.60
     978
    0.60
     expectations
    0.57
     232
    0.57
     201
    0.56
     amended
    0.56
     gardens
    0.56
    Activations Density 0.065%

    No Known Activations