© 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. 28059
    Prev
    Next
    INDEX
    Explanations

    terms related to space and astronomical phenomena

    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
    420
    +0.11
    0.5%
    406
    +0.09
    0.4%
    543
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.01
    477
    +0.09
    0.01
    732
    +0.09
    0.00
    Negative Logits
    INGS
    -0.72
    WOOD
    -0.71
    untled
    -0.70
     guiActiveUn
    -0.67
    lihood
    -0.66
     CARD
    -0.66
    axter
    -0.65
    MENTS
    -0.64
    hov
    -0.63
    CRIP
    -0.62
    POSITIVE LOGITS
    ãĥ¥
    1.24
    ãĥĵ
    0.97
    apolis
    0.92
    ãĥ´
    0.85
    eros
    0.84
    onomy
    0.83
    ãĥ¼ãĥ
    0.83
    ãĥ¼
    0.78
    Ĥ
    0.77
    ¥
    0.73
    Activations Density 0.045%

    No Known Activations