© 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. 14252
    Prev
    Next
    INDEX
    Explanations

    words related to politics, controversial figures, and news articles

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and entities, particularly in political or controversial contexts

    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
     Folder
    -0.59
    noon
    -0.58
     Guinness
    -0.58
    entary
    -0.56
    GROUP
    -0.56
     Starts
    -0.55
     Offline
    -0.55
    iple
    -0.54
     Location
    -0.54
     SG
    -0.54
    POSITIVE LOGITS
    .).
    0.82
     rapists
    0.75
     extremism
    0.71
     rampant
    0.71
     racism
    0.71
    ).[
    0.71
    %.
    0.70
     perpetrated
    0.69
     abhor
    0.68
     authoritarian
    0.68
    Activations Density 1.307%

    No Known Activations