© 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. 12-RES-JB
    11. 2472
    Prev
    Next
    INDEX
    Explanations

    references to personal interactions and experiences, including emotional and familial moments, political discussions, and past events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to personal relationships and social interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    igate
    -0.71
    artifacts
    -0.69
     contested
    -0.67
    à¼
    -0.66
    breaking
    -0.65
    rencies
    -0.65
    urden
    -0.65
    ITH
    -0.63
     disputed
    -0.63
    stroke
    -0.63
    POSITIVE LOGITS
     buddies
    1.22
     buddy
    1.21
     friend
    1.18
     cowork
    1.14
     girlfriends
    1.14
     roommate
    1.12
     girlfriend
    1.10
     friends
    1.10
     coworkers
    1.08
     boyfriend
    1.06
    Activations Density 0.380%

    No Known Activations