© 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. 10-RES-JB
    11. 3053
    Prev
    Next
    INDEX
    Explanations

    questions being posed or situations where asking for information is central

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ask" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zinski
    -0.72
    pite
    -0.68
    ensual
    -0.65
    Ĥ¬
    -0.65
     Nanto
    -0.63
    rongh
    -0.63
     skelet
    -0.61
    cyclop
    -0.61
    rily
    -0.61
    imm
    -0.61
    POSITIVE LOGITS
     questions
    1.36
     rhet
    1.15
     Questions
    1.12
     probing
    1.03
     question
    1.02
     forgiveness
    0.98
     permission
    0.96
    wered
    0.94
     QUEST
    0.91
     nicely
    0.86
    Activations Density 0.055%

    No Known Activations