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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 910
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations or warfare

    oai_token-act-pair · gpt-3.5-turbo

    military actions or operations, particularly offensive maneuvers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lifetime
    -0.94
    cup
    -0.69
    Family
    -0.68
    deal
    -0.68
     exch
    -0.67
     Marketable
    -0.67
    ¢
    -0.66
    Consumer
    -0.66
     Gems
    -0.65
     lifetime
    -0.65
    POSITIVE LOGITS
     besie
    1.13
     patrols
    1.08
     bombardment
    1.02
     raiding
    1.00
     garrison
    0.96
     commander
    0.93
     outpost
    0.93
     encamp
    0.92
     artillery
    0.91
     warfare
    0.90
    Activations Density 0.207%

    No Known Activations