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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22435
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and historical events

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to socio-economic changes and historical context

    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
    ocular
    -0.63
    peed
    -0.62
     tracker
    -0.61
     confir
    -0.61
    endez
    -0.60
    Alert
    -0.60
    ãĤĬ
    -0.60
    Adds
    -0.57
    optional
    -0.57
     Kodi
    -0.57
    POSITIVE LOGITS
     industrialized
    0.97
     democrat
    0.97
     globalization
    0.97
     colonialism
    0.95
     democracies
    0.91
     centuries
    0.89
     liberalism
    0.88
     generations
    0.88
     millennia
    0.88
     democratic
    0.86
    Activations Density 1.319%

    No Known Activations