© 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. 31496
    Prev
    Next
    INDEX
    Explanations

    references to specific quantitative comparisons between patient and control groups

    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
    454
    +0.11
    0.5%
    552
    +0.10
    0.5%
    249
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.04
    594
    +0.10
    0.06
    388
    +0.10
    0.06
    Negative Logits
    advertising
    -0.76
    Disclaimer
    -0.66
    =-=-=-=-
    -0.62
    bats
    -0.61
    ullah
    -0.58
    pmwiki
    -0.57
     fulfillment
    -0.56
     Allaah
    -0.56
    meal
    -0.55
     Kens
    -0.54
    POSITIVE LOGITS
    EStream
    0.82
    xon
    0.77
    stice
    0.74
    xual
    0.72
     Intermediate
    0.72
    è¦ļéĨĴ
    0.67
    ŃĶ
    0.67
    TPPStreamerBot
    0.66
    ription
    0.65
    minus
    0.64
    Activations Density 2.743%

    No Known Activations