© 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. 27813
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their occurrences

    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
    362
    +0.17
    0.8%
    608
    +0.14
    0.7%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.11
    608
    +0.14
    0.09
    493
    +0.11
    0.06
    Negative Logits
    Reviewer
    -0.86
    hin
    -0.79
    ibaba
    -0.78
    ean
    -0.74
    wrap
    -0.73
    Downloadha
    -0.73
    ucket
    -0.71
    netflix
    -0.70
    ãĤ´
    -0.69
    hari
    -0.68
    POSITIVE LOGITS
     respective
    1.77
     own
    1.52
    selves
    1.34
     counterparts
    1.14
     selves
    1.06
     mouths
    1.06
     minds
    1.01
     noses
    1.01
     newfound
    1.00
     newest
    0.99
    Activations Density 0.605%

    No Known Activations