© 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. 1-RES-JB
    11. 20450
    Prev
    Next
    INDEX
    Explanations

    contractions with 'd

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "I'd"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    sis
    -0.79
    topic
    -0.76
    æ³
    -0.76
    é¾įå
    -0.75
    çİĭ
    -0.69
    PDF
    -0.67
    AMP
    -0.66
    SUP
    -0.66
    Offline
    -0.65
    building
    -0.65
    POSITIVE LOGITS
     proble
    0.88
     sugg
    0.83
    ÃĥÃĤ
    0.83
     spoil
    0.75
     gladly
    0.75
    onna
    0.74
     doubtless
    0.73
    escription
    0.72
    ecided
    0.71
     never
    0.71
    Activations Density 0.024%

    No Known Activations