© 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. 22339
    Prev
    Next
    INDEX
    Explanations

    terms related to magnets and magnetic fields

    oai_token-act-pair · gpt-3.5-turbo

    references to magnetic fields

    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
    ELL
    -0.85
    EY
    -0.80
     PsyNet
    -0.77
    ells
    -0.74
     Bog
    -0.74
     Fas
    -0.74
    PE
    -0.73
     Columb
    -0.73
    20439
    -0.73
    ̶
    -0.73
    POSITIVE LOGITS
     magnetic
    1.19
    netic
    1.14
     compass
    1.12
     resonance
    1.07
     Magnetic
    0.95
     coils
    0.93
     coil
    0.92
     magnets
    0.91
     magnet
    0.91
     detachment
    0.90
    Activations Density 0.009%

    No Known Activations