© 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. 30297
    Prev
    Next
    INDEX
    Explanations

    possessive forms, particularly focusing on the word "is" combined with possessive 's

    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
    +0.13
    0.6%
    497
    +0.11
    0.5%
    636
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.07
    120
    +0.11
    0.04
    606
    +0.10
    0.03
    Negative Logits
     assumes
    -0.74
    measures
    -0.72
    00200000
    -0.68
     VIDEOS
    -0.64
     develops
    -0.63
    Shares
    -0.62
    SPONSORED
    -0.61
     determines
    -0.61
     conclude
    -0.60
    terms
    -0.59
    POSITIVE LOGITS
     hottest
    0.82
     Tah
    0.79
     largest
    0.77
     Metropolitan
    0.76
     Rack
    0.74
     Bark
    0.74
     famed
    0.74
     prestigious
    0.73
     tallest
    0.72
     finest
    0.72
    Activations Density 0.371%

    No Known Activations