© 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. 31358
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or values associated with data

    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
    672
    +0.13
    0.6%
    264
    +0.12
    0.5%
    389
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.01
    503
    +0.12
    0.00
    311
    +0.11
    -0.00
    Negative Logits
     commencement
    -0.75
     reconc
    -0.73
     referee
    -0.67
     journals
    -0.66
     editor
    -0.66
     vain
    -0.62
     reinvest
    -0.62
     fateful
    -0.62
     journal
    -0.62
     proc
    -0.61
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    1.07
    idae
    0.89
    aceae
    0.89
    ãĥ¼
    0.82
    population
    0.81
    ãĥĺãĥ©
    0.80
    è¦ļéĨĴ
    0.78
     geographically
    0.78
    asia
    0.77
    ropolitan
    0.76
    Activations Density 0.045%

    No Known Activations