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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2459
    Prev
    Next
    INDEX
    Explanations

    references to militant groups, rebel forces, and armed wings of coalitions

    oai_token-act-pair · gpt-3.5-turbo
    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
    livion
    -0.78
    eston
    -0.77
     screens
    -0.75
     microscope
    -0.72
    ĸļ
    -0.72
     summers
    -0.71
    metry
    -0.71
     checkout
    -0.71
     clocks
    -0.70
    brainer
    -0.70
    POSITIVE LOGITS
     paramilitary
    1.53
     militias
    1.45
     faction
    1.44
     militia
    1.39
     militant
    1.37
     factions
    1.36
     separatist
    1.27
    affiliated
    1.27
     Faction
    1.25
     separatists
    1.24
    Activations Density 0.545%

    No Known Activations