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. 0-RES-JB
    6. 29
    Prev
    Next
    INDEX
    Explanations

    references to civilian individuals or civilian-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to civilian life and safety in conflict contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hook
    -0.73
     Hole
    -0.68
    akings
    -0.65
    Solution
    -0.64
     Sauce
    -0.64
    Strong
    -0.63
     hooks
    -0.63
    sis
    -0.61
    strings
    -0.61
     Ingredients
    -0.61
    POSITIVE LOGITS
     civilian
    3.88
     civilians
    2.34
    military
    1.51
     military
    1.51
    Military
    1.40
    civil
    1.39
    Civil
    1.35
     militar
    1.32
     wartime
    1.26
     Military
    1.19
    Activations Density 0.017%

    No Known Activations