© 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. 7558
    Prev
    Next
    INDEX
    Explanations

    programming structures and functions related to event handling and plotting in a programming context

    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
    373
    +0.15
    0.7%
    314
    +0.11
    0.5%
    622
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.04
    158
    +0.11
    0.04
    314
    +0.11
    0.00
    Negative Logits
    quickShipAvailable
    -0.74
     decline
    -0.66
     withdrawals
    -0.66
     inaccur
    -0.65
     lapse
    -0.60
     tampering
    -0.60
     decay
    -0.60
     dips
    -0.59
     assassinated
    -0.57
     degradation
    -0.57
    POSITIVE LOGITS
    ();
    1.06
     ());
    0.95
    ());
    0.92
     ();
    0.86
    ().
    0.85
    20439
    0.83
    Builder
    0.81
    ()
    0.78
    ({
    0.77
    ("
    0.76
    Activations Density 0.148%

    No Known Activations