© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8403
    Prev
    Next
    INDEX
    Explanations

    phrases related to global scope or international presence

    oai_token-act-pair · gpt-3.5-turbo

    references to the global scale

    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
    votes
    -0.77
     Owners
    -0.70
     Hatch
    -0.62
     Vill
    -0.62
    aid
    -0.62
    ared
    -0.59
     Paid
    -0.59
     Ow
    -0.59
     Davidson
    -0.59
     affirmative
    -0.58
    POSITIVE LOGITS
     globe
    3.64
     glob
    1.59
     hemisphere
    1.54
     planet
    1.48
     continent
    1.47
     continents
    1.42
     world
    1.42
     Globe
    1.41
     Glob
    1.24
     WORLD
    1.18
    Activations Density 0.010%

    No Known Activations