© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 4864
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    specific dates and times

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ļéĨĴ
    -0.53
     exting
    -0.49
    é¾įå¥
    -0.46
    ď
    -0.46
    ÿ
    -0.45
     TheNitrome
    -0.45
    ě
    -0.45
    õ
    -0.45
     externalToEVA
    -0.45
    ė
    -0.45
    POSITIVE LOGITS
     1945
    0.73
     1913
    0.72
     1944
    0.71
     1862
    0.71
     1943
    0.70
     1942
    0.70
     1889
    0.70
     1932
    0.69
     1914
    0.69
     1915
    0.69
    Activations Density 0.491%

    No Known Activations