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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9731
    Prev
    Next
    INDEX
    Explanations

    references to military aircraft, specifically fighter jets

    oai_token-act-pair · gpt-3.5-turbo

    references to military aircraft and jets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cumber
    -0.87
    âĸ¬
    -0.74
     Hallow
    -0.71
     Birch
    -0.70
    ãĥ´
    -0.68
     Alzheimer
    -0.68
     Camden
    -0.67
    Honest
    -0.66
     Territories
    -0.64
     Fine
    -0.63
    POSITIVE LOGITS
     stationed
    1.02
     patrolling
    0.96
    crew
    0.95
     deployed
    0.95
    hops
    0.94
     dispatched
    0.91
    linger
    0.90
    fighters
    0.86
     squadron
    0.86
    piracy
    0.86
    Activations Density 0.052%

    No Known Activations