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. 0-RES-JB
    6. 14288
    Prev
    Next
    INDEX
    Explanations

    words related to geographical regions or areas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "territory."

    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
    LC
    -0.71
    DragonMagazine
    -0.70
    arth
    -0.68
    rate
    -0.66
    Drop
    -0.66
    lift
    -0.65
    Show
    -0.65
    Fra
    -0.65
    RF
    -0.64
    repeat
    -0.64
    POSITIVE LOGITS
     territory
    4.04
     territories
    2.71
     Territory
    2.43
     territorial
    1.88
     Territories
    1.72
     airspace
    1.66
     territ
    1.60
     terrain
    1.46
     Territ
    1.32
     jurisdiction
    1.29
    Activations Density 0.010%

    No Known Activations