© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29554
    Prev
    Next
    INDEX
    Explanations

    references to safety and public health services

    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
    519
    +0.11
    0.5%
    459
    +0.11
    0.5%
    5
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.17
    459
    +0.11
    0.05
    314
    +0.10
    -0.03
    Negative Logits
     Emblem
    -0.78
     Tolkien
    -0.75
     Archangel
    -0.72
     Prophe
    -0.71
    canon
    -0.71
    wreck
    -0.71
     Actress
    -0.71
     Medal
    -0.71
    natureconservancy
    -0.71
     Rebel
    -0.70
    POSITIVE LOGITS
     bathrooms
    1.39
     restrooms
    1.34
     rooms
    1.32
     halls
    1.28
     facilities
    1.25
    rooms
    1.25
     kitchens
    1.19
     spaces
    1.19
     parking
    1.19
     cafes
    1.17
    Activations Density 2.424%

    No Known Activations