© 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. 2-RES-JB
    11. 4229
    Prev
    Next
    INDEX
    Explanations

    places or businesses associated with the word "Bath"

    oai_token-act-pair · gpt-3.5-turbo

    references to bathing and spa-related concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    hift
    -0.67
    ordan
    -0.61
     tune
    -0.60
    eers
    -0.60
    CE
    -0.58
     flare
    -0.57
    è¡
    -0.57
     tuna
    -0.56
    imbabwe
    -0.56
    early
    -0.56
    POSITIVE LOGITS
    urst
    1.50
     Bath
    1.09
    tub
    1.04
    rooms
    0.98
    room
    0.89
    sburgh
    0.87
    lehem
    0.86
    bath
    0.85
     Spa
    0.84
    aby
    0.84
    Activations Density 0.007%

    No Known Activations