© 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. 7-RES-JB
    11. 14234
    Prev
    Next
    INDEX
    Explanations

    celebrities' names

    oai_token-act-pair · gpt-3.5-turbo

    names of celebrities and notable figures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Els
    -0.67
    é£
    -0.66
    orage
    -0.65
    âĸ¬
    -0.65
    Tar
    -0.65
    veyard
    -0.65
    -+-+
    -0.64
    oard
    -0.64
    etheless
    -0.64
    ailability
    -0.64
    POSITIVE LOGITS
     Jr
    0.84
     famously
    0.84
     Presents
    0.83
     III
    0.80
    enegger
    0.79
     QC
    0.78
    hetti
    0.77
     fame
    0.75
     aka
    0.75
    steen
    0.74
    Activations Density 0.197%

    No Known Activations