© 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. 1-RES-JB
    11. 20488
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetism

    oai_token-act-pair · gpt-3.5-turbo

    references to magnets and magnetic properties

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãģį
    -0.81
    PE
    -0.72
    EY
    -0.72
    ----------------------------------------------------------------
    -0.70
    PER
    -0.70
    OWS
    -0.70
    اØ
    -0.69
     Dign
    -0.68
    AKING
    -0.68
    Modern
    -0.67
    POSITIVE LOGITS
     magnet
    1.32
     magnets
    1.30
    netic
    1.03
     tremend
    1.01
     Magnet
    1.00
    ically
    0.98
    ificent
    0.95
    itionally
    0.90
     monop
    0.90
     athlet
    0.89
    Activations Density 0.003%

    No Known Activations