© 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. 8-RES-JB
    11. 7925
    Prev
    Next
    INDEX
    Explanations

    phrases related to the reform or overhaul of systems or institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental and health care system reforms

    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
    isson
    -0.88
    haps
    -0.79
    itars
    -0.76
    és
    -0.75
    loads
    -0.73
    aris
    -0.71
    mart
    -0.70
    aspers
    -0.70
    verb
    -0.69
    00200000
    -0.68
    POSITIVE LOGITS
     workforce
    1.30
     economy
    1.22
     nation
    1.20
     judiciary
    1.04
     country
    1.01
     existing
    1.01
     bureaucracy
    0.99
     remainder
    0.97
     entire
    0.95
     electorate
    0.94
    Activations Density 0.515%

    No Known Activations