© 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. 31441
    Prev
    Next
    INDEX
    Explanations

    instances of geographic terms, specifically relating to regions or provinces

    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
    279
    +0.10
    0.5%
    441
    +0.10
    0.5%
    727
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.02
    530
    +0.10
    0.02
    145
    +0.10
    0.02
    Negative Logits
    notice
    -0.80
    quer
    -0.78
    peat
    -0.77
    esson
    -0.77
    plate
    -0.77
    SAY
    -0.76
    heed
    -0.76
    wagon
    -0.75
    bus
    -0.75
    ghan
    -0.75
    POSITIVE LOGITS
     AA
    0.83
     Authors
    0.81
     Original
    0.71
     Author
    0.68
     Breed
    0.66
     «
    0.66
     Download
    0.66
     Remastered
    0.64
     Feder
    0.64
    hesis
    0.64
    Activations Density 0.206%

    No Known Activations