© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 13809
    Prev
    Next
    INDEX
    Explanations

    words related to destructive forces or societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues or cultural phenomena associated with the term "plague."

    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
    issan
    -0.85
    alez
    -0.81
     Kumar
    -0.75
    ruck
    -0.74
     STATS
    -0.74
    van
    -0.69
    icio
    -0.69
     Cox
    -0.68
    endra
    -0.67
     Nissan
    -0.67
    POSITIVE LOGITS
     plague
    1.83
     Mafia
    1.74
     Masonic
    1.73
     Illuminati
    1.73
     Freem
    1.67
     Rothschild
    1.46
     Templ
    1.37
     Bohem
    1.35
     mafia
    1.34
    asons
    1.31
    Activations Density 0.060%

    No Known Activations