© 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. 22328
    Prev
    Next
    INDEX
    Explanations

    references to rebel groups or forces

    oai_token-act-pair · gpt-3.5-turbo

    references to rebel groups and related terminology

    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
    ographies
    -0.76
    è¯
    -0.73
     Robo
    -0.72
    thora
    -0.70
    ocobo
    -0.69
    ifice
    -0.68
    icrobial
    -0.68
    orgetown
    -0.68
     Loch
    -0.67
    orem
    -0.67
    POSITIVE LOGITS
     factions
    1.08
     militias
    0.99
     rebels
    0.99
     fighters
    0.95
     faction
    0.92
     rebel
    0.89
     milit
    0.88
     leader
    0.88
     shelling
    0.86
     army
    0.86
    Activations Density 0.042%

    No Known Activations