© 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. 13079
    Prev
    Next
    INDEX
    Explanations

    the word "Cass" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cass" and its variations

    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
    gamer
    -0.72
    doms
    -0.71
    scene
    -0.66
    RANT
    -0.66
     IGF
    -0.65
    ndum
    -0.61
    fect
    -0.60
    typ
    -0.60
    tten
    -0.60
    fetched
    -0.60
    POSITIVE LOGITS
    andra
    1.15
    illo
    1.14
    ette
    1.11
    ettes
    1.04
    iop
    1.00
    imir
    1.00
    inelli
    0.99
    essee
    0.96
    aign
    0.96
    idy
    0.95
    Activations Density 0.026%

    No Known Activations