© 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. 3-RES-JB
    11. 3097
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, particularly wars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Civil War

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.81
    gow
    -0.74
    CLASS
    -0.73
    selection
    -0.72
    BIT
    -0.72
    Asset
    -0.70
    CAST
    -0.68
    URES
    -0.68
    WARD
    -0.66
    deck
    -0.66
    POSITIVE LOGITS
     Patton
    0.89
     Era
    0.77
    naire
    0.75
     Royale
    0.74
    venant
    0.73
    becue
    0.71
     Bust
    0.70
     Rite
    0.68
    lord
    0.68
     Graves
    0.67
    Activations Density 0.017%

    No Known Activations