© 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. 1-RES-JB
    11. 20491
    Prev
    Next
    INDEX
    Explanations

    references to TV shows or movies within a specific year

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "in."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ĸļ
    -0.80
    ĨĴ
    -0.78
    Jr
    -0.71
    CLASSIFIED
    -0.65
     Entered
    -0.65
    xual
    -0.65
    Revolution
    -0.64
    âĵĺ
    -0.64
     defe
    -0.63
    Marginal
    -0.63
    POSITIVE LOGITS
    essler
    0.75
    esa
    0.71
    retch
    0.70
     POP
    0.68
    ottest
    0.67
    kell
    0.66
     Osh
    0.65
     Chel
    0.65
     Tsukuyomi
    0.65
     Pon
    0.63
    Activations Density 0.000%

    No Known Activations