© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    the name "Robin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Robin," particularly related to various contexts and references involving Robin Williams and Robin Hood

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.83
    resso
    -0.80
    xual
    -0.76
    chnology
    -0.68
    aeda
    -0.68
    ormon
    -0.67
    ormons
    -0.67
     accur
    -0.66
    pora
    -0.66
    ĵĺ
    -0.65
    POSITIVE LOGITS
     Hood
    1.28
    ette
    1.00
     Williams
    0.87
    istics
    0.86
    alties
    0.85
    aldo
    0.84
     Hanson
    0.84
    ettes
    0.79
    auld
    0.78
     Hob
    0.78
    Activations Density 0.015%

    No Known Activations