© 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. 30292
    Prev
    Next
    INDEX
    Explanations

    references to bugs and errors in various 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
    438
    +0.11
    0.5%
    756
    +0.09
    0.4%
    316
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.11
    0.01
    13
    +0.09
    0.01
    631
    +0.09
    0.01
    Negative Logits
    oshenko
    -0.78
     horm
    -0.66
    pora
    -0.63
     surviving
    -0.63
     nudity
    -0.63
     solder
    -0.62
     ende
    -0.61
     PLA
    -0.61
     Reincarn
    -0.60
     wasteland
    -0.59
    POSITIVE LOGITS
    eca
    1.10
    gers
    1.09
    ger
    1.04
    istics
    0.99
    ifact
    0.94
    ging
    0.86
    yssey
    0.85
    imen
    0.84
    ges
    0.84
    gy
    0.82
    Activations Density 0.058%

    No Known Activations