© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 7736
    Prev
    Next
    INDEX
    Explanations

    entities related to European politics, specifically Members of the European Parliament (MEPs) and councillors

    oai_token-act-pair · gpt-3.5-turbo

    references to political roles and titles, specifically those related to Members of the European Parliament (MEPs) and councillors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stakes
    -0.75
     Rubber
    -0.73
     American
    -0.69
     USA
    -0.66
    Texas
    -0.63
    gins
    -0.63
     America
    -0.63
     Wall
    -0.62
     fulfillment
    -0.61
    American
    -0.61
    POSITIVE LOGITS
     MEP
    3.10
     councillor
    3.07
     councillors
    2.84
     MLA
    1.97
     MPs
    1.77
    cill
    1.58
     UKIP
    1.48
     mayors
    1.40
     Coun
    1.38
     TDs
    1.36
    Activations Density 0.008%

    No Known Activations