© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES_POST_32K-OAI
    11. 29279
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire or requests involving "you" and "us."

    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
    566
    +0.13
    0.6%
    348
    +0.10
    0.5%
    493
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.05
    15
    +0.10
    0.04
    566
    +0.10
    0.04
    Negative Logits
     srfAttach
    -0.75
    ibe
    -0.74
    guyen
    -0.72
    VIDIA
    -0.68
    uyomi
    -0.65
    ugh
    -0.65
    ggles
    -0.64
    iversal
    -0.62
    actionDate
    -0.62
     Sina
    -0.61
    POSITIVE LOGITS
     gone
    1.03
     deported
    1.02
     dead
    1.01
     punished
    0.96
     kidding
    0.92
     locked
    0.91
     stuck
    0.90
     silenced
    0.90
     prosecuted
    0.88
     killed
    0.88
    Activations Density 0.373%

    No Known Activations