Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16828
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and events in Iraq

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilde
    -1.26
    uckland
    -0.98
     Butterfly
    -0.97
     Cthulhu
    -0.95
     bunny
    -0.92
     Vermont
    -0.92
     Luigi
    -0.90
     Duc
    -0.89
     Leica
    -0.88
    chester
    -0.86
    POSITIVE LOGITS
     Baghdad
    2.14
     Iraqi
    2.12
     Mosul
    2.07
    Iraq
    2.04
     Kurdistan
    1.94
     Iraqis
    1.86
     Kurdish
    1.86
     Kurds
    1.80
     Iraq
    1.79
     Shiite
    1.76
    Activations Density 0.295%

    No Known Activations