© 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. 31509
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "honor" in various forms

    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
    682
    +0.11
    0.5%
    376
    +0.10
    0.5%
    33
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.03
    546
    +0.10
    0.02
    735
    +0.10
    0.02
    Negative Logits
     Zot
    -0.69
     Barbarian
    -0.68
     Spray
    -0.68
     Leilan
    -0.66
     fluids
    -0.63
    backer
    -0.63
     saline
    -0.62
     asteroids
    -0.61
     materials
    -0.59
     Princess
    -0.59
    POSITIVE LOGITS
    olulu
    1.48
    esty
    1.32
    orable
    1.27
    ours
    1.22
    ouring
    1.10
    kers
    1.05
    kies
    1.04
    cho
    1.03
    orem
    1.03
    oured
    1.00
    Activations Density 0.080%

    No Known Activations