© 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. 3-RES-JB
    6. 12325
    Prev
    Next
    INDEX
    Explanations

    mentions of conflict, specifically war-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to war and associated crimes

    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
    */(
    -1.05
    aye
    -0.86
    veland
    -0.76
    igans
    -0.75
    uyomi
    -0.74
     Helpful
    -0.73
     (<
    -0.71
    )=(
    -0.69
    tera
    -0.67
    evin
    -0.67
    POSITIVE LOGITS
     Armageddon
    0.74
     raged
    0.71
    adesh
    0.70
     Yugoslavia
    0.69
     Roses
    0.69
     liberation
    0.64
     Legion
    0.63
    istan
    0.63
     retribution
    0.62
     dawn
    0.62
    Activations Density 0.275%

    No Known Activations