© 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. 24296
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city of Vancouver

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Vancouver" and its associated sports team, the Canucks

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ktop
    -0.81
    mble
    -0.78
    ppo
    -0.75
    maid
    -0.72
     discipl
    -0.70
    finding
    -0.66
    mons
    -0.66
    bler
    -0.66
    lein
    -0.64
    ãĥĻ
    -0.63
    POSITIVE LOGITS
     Canucks
    1.30
     Island
    1.09
     Lumpur
    1.02
     Province
    1.00
     Vancouver
    0.94
    ancouver
    0.89
    ites
    0.88
    atche
    0.86
     Beckham
    0.85
     Coastal
    0.84
    Activations Density 0.024%

    No Known Activations