© 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. 3-RES-JB
    11. 634
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Do."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Do" followed by a question or directive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.76
    Gaza
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    ulatory
    -0.70
    workshop
    -0.70
    ItemTracker
    -0.68
    )=(
    -0.67
    ICAN
    -0.66
    boarding
    -0.65
     Preferences
    -0.65
    POSITIVE LOGITS
    omsday
    1.21
    herty
    1.11
    ppel
    1.06
    zens
    1.05
    oway
    0.91
    oley
    0.90
    lyak
    0.89
    lez
    0.89
    ctr
    0.88
    oms
    0.84
    Activations Density 0.049%

    No Known Activations