© 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. 8-RES_POST_32K-OAI
    11. 8422
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or characters associated with certain achievements or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    649
    +0.14
    0.7%
    553
    +0.11
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.04
    288
    +0.11
    0.05
    48
    +0.10
    0.03
    Negative Logits
    20439
    -0.83
    utters
    -0.73
    ================================================================
    -0.65
    ãĤ¨ãĥ«
    -0.64
    Package
    -0.64
    ãĥ¼ãĥ³
    -0.63
    ascript
    -0.62
    BOOK
    -0.62
    alities
    -0.62
    ttes
    -0.61
    POSITIVE LOGITS
    Rush
    0.71
    lords
    0.70
     StarCraft
    0.68
     Confederacy
    0.67
     larvae
    0.65
    lord
    0.64
    hack
    0.64
    ener
    0.63
    Lord
    0.62
    craft
    0.62
    Activations Density 0.279%

    No Known Activations