© 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. 8-RES_POST_32K-OAI
    11. 8549
    Prev
    Next
    INDEX
    Explanations

    instances of the word "It" emphasizing the subject of a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    640
    +0.10
    0.5%
    174
    +0.10
    0.4%
    287
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.10
    571
    +0.10
    0.10
    676
    +0.09
    0.10
    Negative Logits
    natureconservancy
    -0.73
     guiActiveUnfocused
    -0.68
     weather
    -0.60
     BELOW
    -0.60
     bud
    -0.59
     BRE
    -0.56
    Finish
    -0.55
     SOU
    -0.55
    EngineDebug
    -0.55
     Annotations
    -0.54
    POSITIVE LOGITS
     furthermore
    1.06
     therefore
    0.99
    gemony
    0.95
    also
    0.95
     moreover
    0.94
    hor
    0.88
     also
    0.88
    ogether
    0.85
    Then
    0.82
     certainly
    0.81
    Activations Density 0.264%

    No Known Activations