© 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. 10-RES-JB
    11. 13985
    Prev
    Next
    INDEX
    Explanations

    phrases related to state government, policies, and interactions with local entities

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or state-related matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogle
    -0.80
    eger
    -0.80
    aurus
    -0.79
    edin
    -0.78
    icago
    -0.77
    lio
    -0.73
    »Ĵ
    -0.73
    nob
    -0.72
    poons
    -0.70
    hene
    -0.69
    POSITIVE LOGITS
     legislatures
    1.29
    wide
    1.23
     legislators
    1.20
     troopers
    1.18
     governments
    1.11
     legislator
    1.07
     legislature
    1.07
     lawmakers
    1.05
     trooper
    1.04
     Legisl
    1.03
    Activations Density 0.059%

    No Known Activations