© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16450
    Prev
    Next
    INDEX
    Explanations

    contractions and abbreviations paired with quotations or apostrophes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the apostrophe character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.75
     eclipse
    -0.70
    rador
    -0.64
    İĭ
    -0.62
    Ļ½
    -0.61
    isphere
    -0.60
     isolated
    -0.60
    conservancy
    -0.59
     rematch
    -0.58
     inhibited
    -0.58
    POSITIVE LOGITS
    ',
    0.82
    Mech
    0.79
    bor
    0.77
    Cause
    0.77
    Allah
    0.73
    Brien
    0.73
    nos
    0.72
    soDeliveryDate
    0.71
    Interstitial
    0.71
    -'
    0.70
    Activations Density 0.061%

    No Known Activations