© 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. 32544
    Prev
    Next
    INDEX
    Explanations

    specific food establishments or dining experiences

    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
    145
    +0.10
    0.5%
    247
    +0.10
    0.4%
    648
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.09
    145
    +0.10
    0.08
    659
    +0.09
    0.07
    Negative Logits
    inventoryQuantity
    -0.85
    REDACTED
    -0.77
    20439
    -0.75
    overe
    -0.73
     cytok
    -0.71
     constitu
    -0.71
     equations
    -0.71
     graphs
    -0.70
     pollutants
    -0.70
     diagrams
    -0.70
    POSITIVE LOGITS
     Cafe
    1.72
     Café
    1.63
     Lounge
    1.58
     Tavern
    1.54
     Restaurant
    1.53
     Grill
    1.51
     Pub
    1.45
     nightclub
    1.39
     Brewery
    1.37
     Hotel
    1.37
    Activations Density 1.058%

    No Known Activations