© 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. 27785
    Prev
    Next
    INDEX
    Explanations

    instances of the word "brought" and its variations

    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
    439
    +0.10
    0.4%
    251
    +0.09
    0.4%
    756
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.04
    12
    +0.09
    0.03
    761
    +0.09
    0.03
    Negative Logits
    schild
    -0.69
    isoft
    -0.63
     Tribal
    -0.61
    asus
    -0.61
    ims
    -0.59
    conservancy
    -0.59
    apo
    -0.58
    uchs
    -0.57
    pmwiki
    -0.57
     Borough
    -0.57
    POSITIVE LOGITS
     forth
    1.13
     forward
    1.05
    iment
    0.92
     home
    0.85
     hither
    0.83
     back
    0.83
     down
    0.80
    iments
    0.77
     up
    0.76
    down
    0.74
    Activations Density 0.109%

    No Known Activations