© 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. 24286
    Prev
    Next
    INDEX
    Explanations

    locations where activities or items are found, such as galleries, schools, or stores

    oai_token-act-pair · gpt-3.5-turbo

    locations and places where activities or events occur

    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
    teness
    -0.74
    maxwell
    -0.66
     Rebellion
    -0.61
    aughs
    -0.60
    anan
    -0.59
    tein
    -0.59
    rification
    -0.58
     appetite
    -0.57
    ozy
    -0.57
     Patriarch
    -0.56
    POSITIVE LOGITS
    hips
    1.36
    hops
    1.28
    chool
    1.25
    paces
    1.24
     alike
    1.02
    hare
    1.01
     nationwide
    1.00
    afety
    1.00
    hip
    0.98
    mith
    0.95
    Activations Density 0.353%

    No Known Activations