© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3602
    Prev
    Next
    INDEX
    Explanations

    keywords related to various aspects of physics and physiology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical sciences and physiological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    corn
    -0.73
    noon
    -0.69
    mast
    -0.68
     Lions
    -0.68
    yrinth
    -0.67
    holder
    -0.66
    sg
    -0.66
     Imperium
    -0.65
     Proposition
    -0.65
     Garrison
    -0.65
    POSITIVE LOGITS
    Phys
    1.25
     mathemat
    1.12
    icist
    1.05
     Phys
    1.03
    iology
    1.01
    phys
    0.99
    htaking
    0.92
    ophys
    0.92
    odynam
    0.90
    Downloadha
    0.90
    Activations Density 0.007%

    No Known Activations