© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    mentions of various embassies in different countries

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic entities or relationships

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    tc
    -0.70
     shenan
    -0.67
     nausea
    -0.66
    lc
    -0.65
    ascript
    -0.64
    ionic
    -0.64
    letal
    -0.64
     handc
    -0.63
    amac
    -0.63
     Bronx
    -0.63
    POSITIVE LOGITS
     UNESCO
    1.05
     abroad
    1.04
     Nato
    0.94
     foreigners
    0.91
     foreign
    0.84
     international
    0.84
     separatists
    0.83
     NATO
    0.83
     neighbouring
    0.82
    Foreign
    0.80
    Activations Density 0.690%

    No Known Activations