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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 11597
    Prev
    Next
    INDEX
    Explanations

    verbs related to attracting or seeking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to attracting attention or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchi
    -0.77
    nia
    -0.76
    uga
    -0.65
    MD
    -0.64
     Doctors
    -0.64
     Bradley
    -0.63
    Kit
    -0.62
     Printing
    -0.61
     printing
    -0.61
    ken
    -0.61
    POSITIVE LOGITS
     attract
    3.59
     attracting
    2.54
     attracts
    2.51
     attracted
    1.96
     lure
    1.93
     attraction
    1.49
     stimulate
    1.27
     attractive
    1.26
     attractions
    1.22
     lured
    1.21
    Activations Density 0.012%

    No Known Activations