© 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. 11-RES-JB
    11. 12927
    Prev
    Next
    INDEX
    Explanations

    social media platforms, specifically Facebook

    oai_token-act-pair · gpt-3.5-turbo

    references to social media, particularly Facebook

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    nces
    -0.97
    geries
    -0.64
    heny
    -0.64
    onse
    -0.63
    rate
    -0.62
    xual
    -0.60
    baugh
    -0.59
    inav
    -0.59
    Ļ½
    -0.58
    ersen
    -0.58
    POSITIVE LOGITS
     Messenger
    0.86
     Page
    0.81
     PAGE
    0.78
     Event
    0.77
     page
    0.75
    icus
    0.75
     messenger
    0.74
    edin
    0.74
     Groups
    0.72
    nect
    0.72
    Activations Density 0.023%

    No Known Activations