© 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. 31844
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly those significant to a narrative or context

    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
    192
    +0.12
    0.5%
    548
    +0.10
    0.5%
    741
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.12
    -0.00
    394
    +0.10
    0.00
    521
    +0.10
    0.00
    Negative Logits
    rer
    -0.83
    yrinth
    -0.82
    ribe
    -0.81
    ter
    -0.78
    eda
    -0.75
    ioned
    -0.75
    emet
    -0.75
    ional
    -0.75
    ifer
    -0.74
    rophe
    -0.73
    POSITIVE LOGITS
     Kitty
    0.96
     Page
    0.64
     Kitt
    0.63
     Ku
    0.59
     Fleet
    0.59
     Blue
    0.59
     Shy
    0.58
     Pry
    0.57
    adelphia
    0.57
     Bub
    0.57
    Activations Density 0.035%

    No Known Activations