© 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. 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. 21746
    Prev
    Next
    INDEX
    Explanations

    the word "does"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "does."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Quarter
    -0.71
    rum
    -0.70
    hung
    -0.70
    haul
    -0.68
     Unle
    -0.67
     Vers
    -0.66
     Methods
    -0.66
     Canal
    -0.64
     Commun
    -0.64
    hol
    -0.63
    POSITIVE LOGITS
    ĸļ
    1.01
    omething
    0.91
    oley
    0.89
     confir
    0.86
    omsday
    0.85
     not
    0.84
    ppel
    0.83
    notation
    0.81
    lez
    0.81
    berra
    0.78
    Activations Density 0.037%

    No Known Activations