© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29742
    Prev
    Next
    INDEX
    Explanations

    specific references to Canadian provinces and geographical data

    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
    373
    +0.15
    0.7%
    142
    +0.10
    0.5%
    125
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.15
    0.01
    125
    +0.10
    0.01
    504
    +0.10
    0.01
    Negative Logits
    merce
    -0.93
    DragonMagazine
    -0.90
    antz
    -0.85
    omething
    -0.82
    raz
    -0.82
    orks
    -0.80
    316
    -0.79
    rez
    -0.79
    pun
    -0.79
    wcs
    -0.79
    POSITIVE LOGITS
     1
    0.85
     Remastered
    0.73
     PTS
    0.68
     Alphabet
    0.67
     Privacy
    0.65
     SECTION
    0.65
     Pokémon
    0.64
     Toggle
    0.63
     HOME
    0.63
     Trainer
    0.62
    Activations Density 0.093%

    No Known Activations