© 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. 11-RES-JB
    11. 12747
    Prev
    Next
    INDEX
    Explanations

    temporal phrases denoting specific times or moments

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ®
    -0.67
     Reprodu
    -0.65
    ught
    -0.62
    opter
    -0.59
    Resource
    -0.59
     Pattern
    -0.58
     Heck
    -0.58
    reen
    -0.56
    nation
    -0.55
     Especially
    -0.55
    POSITIVE LOGITS
     weeks
    0.99
     hours
    0.98
     before
    0.96
     shy
    0.96
     metres
    0.95
     days
    0.95
    icia
    0.90
     minutes
    0.89
     months
    0.89
     prior
    0.87
    Activations Density 0.042%

    No Known Activations