© 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. 20501
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "do" in various contexts

    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
    Reviewer
    -0.95
    ONSORED
    -0.72
     Handling
    -0.70
     chrom
    -0.65
    ï¸ı
    -0.64
    ICAN
    -0.64
    Merit
    -0.64
     Giant
    -0.64
     Taiwanese
    -0.63
     Pwr
    -0.63
    POSITIVE LOGITS
    omsday
    1.13
    ppel
    1.04
    ctors
    1.04
    ctr
    1.04
    zin
    1.02
    pez
    0.95
    zens
    0.93
    vernment
    0.88
    herty
    0.88
    lez
    0.87
    Activations Density 0.012%

    No Known Activations