© 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. 10226
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific hormone

    oai_token-act-pair · gpt-3.5-turbo

    terms related to olfactory senses, particularly focusing on scents and their effects

    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
     Ll
    -0.85
     Caf
    -0.81
     Tomorrow
    -0.76
     Hust
    -0.75
     Tracker
    -0.73
     Ley
    -0.72
     Imper
    -0.72
     Hurt
    -0.71
     Sund
    -0.71
     Vend
    -0.71
    POSITIVE LOGITS
    uries
    1.08
    oscopic
    1.02
    ophobic
    0.96
    urable
    0.96
    otype
    0.91
    aning
    0.89
    onic
    0.89
    otyp
    0.88
    abilities
    0.87
    ocytes
    0.85
    Activations Density 0.166%

    No Known Activations