© 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. 10-RES_POST_32K-OAI
    11. 28229
    Prev
    Next
    INDEX
    Explanations

    expressions of moderate to high degrees of quality or satisfaction

    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
    676
    +0.12
    0.5%
    94
    +0.09
    0.4%
    190
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.04
    227
    +0.09
    0.03
    230
    +0.09
    0.03
    Negative Logits
     Cosponsors
    -0.83
    ocene
    -0.81
    artments
    -0.80
    letters
    -0.79
    ttes
    -0.76
    Si
    -0.76
    Os
    -0.75
    ulia
    -0.75
    Newsletter
    -0.74
    LES
    -0.73
    POSITIVE LOGITS
     darn
    1.02
     standard
    1.01
     damn
    0.91
     tame
    0.87
     straightforward
    0.85
     unrem
    0.85
     evenly
    0.85
     legit
    0.83
     decent
    0.83
     penny
    0.82
    Activations Density 0.120%

    No Known Activations