© 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. 1-RES-JB
    11. 21148
    Prev
    Next
    INDEX
    Explanations

    mentions of specific TV show segments called "Question Time"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Question" and its variations, indicating a focus on inquiries or interrogative contexts

    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
    milo
    -0.80
    emetery
    -0.75
     volunte
    -0.73
    é¾
    -0.68
    ovie
    -0.67
    ript
    -0.67
    olson
    -0.66
     externalToEVAOnly
    -0.65
    ORK
    -0.65
    odium
    -0.64
    POSITIVE LOGITS
    naire
    1.52
    naires
    1.14
     Question
    1.08
    Question
    1.02
     Questions
    1.00
    abal
    0.82
    aire
    0.78
    aires
    0.74
    erion
    0.74
    estamp
    0.72
    Activations Density 0.010%

    No Known Activations