© 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 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. 28286
    Prev
    Next
    INDEX
    Explanations

    instances of the word "provided" and related terms indicating the act of offering or making available

    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
    756
    +0.12
    0.6%
    679
    +0.10
    0.5%
    597
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.12
    0.01
    317
    +0.10
    0.03
    677
    +0.10
    0.03
    Negative Logits
    kson
    -0.77
    ctors
    -0.71
    crow
    -0.64
    prints
    -0.61
    lines
    -0.61
    lifting
    -0.58
    nces
    -0.56
     waged
    -0.56
    pora
    -0.56
    aders
    -0.56
    POSITIVE LOGITS
    irrel
    0.70
     through
    0.70
     below
    0.67
     via
    0.66
     THR
    0.66
     voluntarily
    0.65
     herein
    0.65
    DragonMagazine
    0.64
    unal
    0.63
     anecd
    0.62
    Activations Density 0.269%

    No Known Activations