© 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. 8-RES-JB
    11. 14150
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a chronological sequence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "On" followed by numbers

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MODE
    -0.66
     cruc
    -0.64
    RL
    -0.60
    ennes
    -0.59
     choke
    -0.59
    amus
    -0.56
    $$
    -0.55
    amount
    -0.55
    lements
    -0.55
    Reports
    -0.55
    POSITIVE LOGITS
    slaught
    1.30
     behalf
    1.21
    coming
    1.16
     occasion
    1.07
    look
    1.06
    etime
    1.04
    eness
    0.95
    sight
    0.93
     July
    0.92
    shore
    0.91
    Activations Density 0.070%

    No Known Activations