© 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. 10-RES_POST_32K-OAI
    11. 29257
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and acronyms related to environmental issues and biology

    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
    718
    +0.10
    0.5%
    485
    +0.10
    0.5%
    637
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.10
    0.02
    566
    +0.10
    0.02
    314
    +0.09
    -0.00
    Negative Logits
    naire
    -0.91
    artz
    -0.89
    ows
    -0.82
    ingly
    -0.77
    heid
    -0.77
    phas
    -0.72
    atche
    -0.71
    lain
    -0.71
    come
    -0.71
    rity
    -0.70
    POSITIVE LOGITS
    X
    0.88
    E
    0.84
    FTWARE
    0.82
    I
    0.78
    FU
    0.77
    Ws
    0.77
    mega
    0.75
    CC
    0.75
    ECD
    0.71
    V
    0.71
    Activations Density 0.145%

    No Known Activations