© 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. 32744
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    334
    +0.12
    0.5%
    493
    +0.10
    0.5%
    76
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.10
    608
    +0.10
    0.09
    385
    +0.09
    0.07
    Negative Logits
     understatement
    -0.95
    lly
    -0.81
     <+
    -0.79
    \\\\\\\\
    -0.79
    etheless
    -0.77
    :{
    -0.76
    must
    -0.76
     è£ıè
    -0.67
    since
    -0.67
    fusc
    -0.67
    POSITIVE LOGITS
     dust
    1.14
     doors
    1.12
     timer
    0.99
     curtain
    0.99
     tide
    0.99
     lights
    0.93
    rils
    0.91
     bells
    0.91
     rains
    0.88
     hostilities
    0.88
    Activations Density 0.548%

    No Known Activations