© 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. 12968
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to global political events or figures

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities or political affiliations

    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
    Ó
    -0.86
    iphate
    -0.82
    same
    -0.81
    ramid
    -0.78
    edin
    -0.75
    atron
    -0.74
    Ïī
    -0.73
    illet
    -0.73
    arial
    -0.71
    ructure
    -0.71
    POSITIVE LOGITS
     officials
    1.31
     commentators
    1.23
     observers
    1.21
     analysts
    1.19
     lawmakers
    1.16
     negotiators
    1.15
     historians
    1.14
     researchers
    1.13
     investigators
    1.13
     diplomats
    1.13
    Activations Density 0.340%

    No Known Activations