© 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. 8-RES-JB
    11. 13139
    Prev
    Next
    INDEX
    Explanations

    references to people named "Tyler"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tyler."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĤ¦ãĤ¹
    -0.83
    ãĥīãĥ©
    -0.80
    circ
    -0.72
    Ú
    -0.72
    ktop
    -0.69
    terior
    -0.68
    ãĤ»
    -0.68
    mble
    -0.68
    Ö¼
    -0.68
    fm
    -0.67
    POSITIVE LOGITS
     Wink
    0.95
     Tyler
    0.85
    stown
    0.78
     Adams
    0.78
     Perry
    0.78
     Shields
    0.78
     Vaugh
    0.77
     Cow
    0.76
     Chandler
    0.75
     Haley
    0.74
    Activations Density 0.024%

    No Known Activations