© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26526
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "met" and variations related to databases and measurement in a coding context

    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
    497
    +0.12
    0.5%
    464
    +0.09
    0.4%
    564
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.00
    167
    +0.09
    0.01
    289
    +0.09
    0.01
    Negative Logits
    ãĤ´ãĥ³
    -0.72
     inaction
    -0.68
    uci
    -0.65
    enegger
    -0.63
    UCT
    -0.63
    OHN
    -0.63
    handed
    -0.62
     Hera
    -0.61
     mistaken
    -0.60
    ACTED
    -0.60
    POSITIVE LOGITS
    adata
    1.00
    rix
    0.98
    abytes
    0.90
    etime
    0.88
    vern
    0.86
    Info
    0.86
    ries
    0.85
    agram
    0.84
    estamp
    0.84
    agraph
    0.81
    Activations Density 0.624%

    No Known Activations