© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10328
    Prev
    Next
    INDEX
    Explanations

    questions or statements posing a question

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or questions posed within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rites
    -0.86
    orpor
    -0.76
    ufact
    -0.71
    gian
    -0.64
    odka
    -0.62
    gewater
    -0.62
    lett
    -0.61
    rylic
    -0.61
     corrid
    -0.60
    ols
    -0.59
    POSITIVE LOGITS
    naires
    1.73
    naire
    1.50
     mark
    1.09
     posed
    1.09
    answer
    1.02
     answered
    1.01
     unanswered
    1.00
     asked
    1.00
    mark
    0.98
     arises
    0.92
    Activations Density 0.044%

    No Known Activations