© 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. 6156
    Prev
    Next
    INDEX
    Explanations

    instances of the word "set" in various contexts

    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
    +0.12
    0.6%
    337
    +0.10
    0.4%
    730
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.03
    113
    +0.10
    0.03
    416
    +0.10
    0.03
    Negative Logits
    outh
    -0.66
    erous
    -0.66
    icht
    -0.64
     exerc
    -0.60
     smoot
    -0.58
     ende
    -0.57
    ished
    -0.56
    ocker
    -0.56
    amus
    -0.56
    ente
    -0.56
    POSITIVE LOGITS
     aboard
    0.70
    reon
    0.66
    bridge
    0.66
    square
    0.66
    Credits
    0.66
     Banner
    0.64
     Roads
    0.64
    years
    0.63
     nearer
    0.62
     Rez
    0.61
    Activations Density 0.242%

    No Known Activations