© 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 EvalsExportsAPI 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. 6301
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" associated with pauses or interruptions

    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
    708
    +0.10
    0.4%
    273
    +0.09
    0.4%
    156
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.03
    500
    +0.09
    0.03
    301
    +0.09
    0.02
    Negative Logits
    ifice
    -0.71
    ä¸ī
    -0.66
    MSN
    -0.63
    ãĥ¥
    -0.62
    ography
    -0.61
     obser
    -0.61
    ãĥĺãĥ©
    -0.60
     constitu
    -0.60
    ufact
    -0.60
     Reform
    -0.59
    POSITIVE LOGITS
    away
    1.28
    aways
    1.06
    neck
    1.05
    agne
    1.01
    robe
    0.98
    fast
    0.98
    water
    0.93
    outs
    0.88
    draft
    0.88
    opian
    0.87
    Activations Density 0.193%

    No Known Activations