© 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. 9-RES-JB
    11. 13530
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially with common names like Dan, Ray, and Jim, combined with surnames that often have additional characters, such as Devine, Sheero, and Mcint

    oai_token-act-pair · gpt-3.5-turbo

    instances of proper nouns and characters' names

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Balt
    -0.73
    izoph
    -0.72
     Citiz
    -0.69
     Adin
    -0.69
    ECTION
    -0.68
    Els
    -0.68
     Seym
    -0.67
    Sit
    -0.63
    CEPT
    -0.63
    Region
    -0.62
    POSITIVE LOGITS
     Jr
    1.09
    enegger
    1.08
    iewicz
    0.99
     famously
    0.94
     himself
    0.89
     QC
    0.89
     testified
    0.89
    meier
    0.89
    zzi
    0.87
    kamp
    0.86
    Activations Density 0.373%

    No Known Activations