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. 0-RES-JB
    6. 5568
    Prev
    Next
    INDEX
    Explanations

    words related to military figures and equipment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military ranks and vehicles

    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
     Blackwell
    -0.83
    itten
    -0.77
    afer
    -0.72
     Machina
    -0.70
    etter
    -0.68
    bnb
    -0.67
     Craigslist
    -0.67
    wk
    -0.67
     commuter
    -0.66
    Jamie
    -0.65
    POSITIVE LOGITS
     generals
    2.62
     tanks
    2.00
     Colonel
    1.72
     Tanks
    1.64
     colonel
    1.63
     Gener
    1.57
     marines
    1.21
     commanders
    1.19
     soldiers
    1.17
     armies
    1.08
    Activations Density 0.024%

    No Known Activations