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. 3-RES-JB
    6. 7638
    Prev
    Next
    INDEX
    Explanations

    mentions of military actions and operations, specifically related to ground forces and interventions

    oai_token-act-pair · gpt-3.5-turbo

    references to military operations and ground forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Marg
    -0.79
    ¢
    -0.78
    Brew
    -0.77
    Shares
    -0.75
     Shirley
    -0.73
    çͰ
    -0.72
     Deg
    -0.70
    é¾įå
    -0.70
     Parables
    -0.69
     salon
    -0.69
    POSITIVE LOGITS
     commanders
    1.11
     commander
    1.09
     deployments
    1.07
     milit
    1.06
     reconnaissance
    1.05
     counterterrorism
    1.05
     troops
    1.02
     Operations
    1.01
     patrols
    1.00
     deployment
    0.99
    Activations Density 0.145%

    No Known Activations