Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4865
    Prev
    Next
    INDEX
    Explanations

    words related to questioning or doubts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emetery
    -0.92
    oiler
    -0.91
    rites
    -0.82
    ufact
    -0.78
    ategory
    -0.75
    ammy
    -0.70
    aghetti
    -0.70
    ghai
    -0.69
    ohyd
    -0.69
    anking
    -0.68
    POSITIVE LOGITS
    naires
    1.08
     whether
    0.87
     questioning
    0.84
     questions
    0.81
    naire
    0.78
     why
    0.76
     unanswered
    0.75
    ively
    0.75
     skepticism
    0.74
     him
    0.73
    Activations Density 0.037%

    No Known Activations