© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9550
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to do" followed by various actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.72
    lights
    -0.71
    dayName
    -0.65
    wagen
    -0.63
     Bullets
    -0.63
    theless
    -0.63
    mares
    -0.61
     Immunity
    -0.59
     TCU
    -0.58
     FIR
    -0.58
    POSITIVE LOGITS
    omsday
    0.97
    pez
    0.90
    ppel
    0.85
    lez
    0.85
    ozy
    0.84
    le
    0.84
     favors
    0.84
    omething
    0.83
     justice
    0.80
    ggy
    0.80
    Activations Density 0.073%

    No Known Activations