© 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. 18810
    Prev
    Next
    INDEX
    Explanations

    questions in the text, with a particular emphasis on questions ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions within the text

    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
    aper
    -0.78
    enium
    -0.77
    apers
    -0.72
     ankles
    -0.71
     encount
    -0.71
    onding
    -0.70
    eping
    -0.69
    alled
    -0.69
    aled
    -0.69
     glim
    -0.68
    POSITIVE LOGITS
    .?
    0.97
     Surely
    0.93
     Why
    0.92
     Where
    0.87
     Probably
    0.86
     Certainly
    0.86
     Perhaps
    0.85
     Nope
    0.84
    ����
    0.84
     Surprisingly
    0.84
    Activations Density 0.095%

    No Known Activations