© 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. 6-RES-JB
    11. 13790
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Iraq" or entities related to Iraq in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Iraqi government and military

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.96
    ritch
    -0.86
    smanship
    -0.83
    asonable
    -0.77
    aminer
    -0.77
    oldemort
    -0.76
    eries
    -0.76
    weeney
    -0.76
    alty
    -0.76
    verett
    -0.75
    POSITIVE LOGITS
     Kurdistan
    1.26
     Hussein
    0.95
     Kurds
    0.93
     Arab
    0.90
     Kurd
    0.89
     Iraqi
    0.89
    apolis
    0.88
    istani
    0.87
     Kurdish
    0.85
     insurgents
    0.83
    Activations Density 0.013%

    No Known Activations