© 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. 28139
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes related to data entries or classifications

    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
    448
    +0.13
    0.6%
    591
    +0.10
    0.5%
    287
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.13
    0.01
    316
    +0.10
    0.02
    620
    +0.10
    0.01
    Negative Logits
     outweigh
    -0.73
    emouth
    -0.70
     descent
    -0.69
    reditary
    -0.68
    ebus
    -0.67
    wagen
    -0.66
     plateau
    -0.64
     trump
    -0.64
    ggles
    -0.64
    oÄŁ
    -0.63
    POSITIVE LOGITS
    800
    0.79
    467
    0.78
    474
    0.77
     xx
    0.75
    365
    0.75
    94
    0.74
    430
    0.74
    2020
    0.74
    870
    0.73
    630
    0.71
    Activations Density 0.204%

    No Known Activations