© 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. 26929
    Prev
    Next
    INDEX
    Explanations

    phrases that include the term "couple" with varying numerical contexts

    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
    19
    +0.13
    0.6%
    45
    +0.10
    0.4%
    8
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.13
    0.04
    19
    +0.10
    0.03
    223
    +0.08
    0.04
    Negative Logits
    schild
    -0.83
    eton
    -0.76
    emouth
    -0.76
    ichick
    -0.72
    IAS
    -0.72
    andise
    -0.71
    leneck
    -0.71
    enegger
    -0.68
    isu
    -0.67
    sein
    -0.67
    POSITIVE LOGITS
     dozen
    1.62
     hundred
    1.61
     thousand
    1.40
     weeks
    1.22
     months
    1.09
     inches
    1.01
    dozen
    0.98
     centuries
    0.97
     decades
    0.96
     days
    0.95
    Activations Density 0.161%

    No Known Activations