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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3253
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically islands

    oai_token-act-pair · gpt-3.5-turbo

    references to islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.89
    chel
    -0.81
    pheus
    -0.76
    acher
    -0.74
    nyder
    -0.74
    м
    -0.72
    chen
    -0.72
    itbart
    -0.71
    keley
    -0.70
    ilyn
    -0.70
    POSITIVE LOGITS
     Islands
    1.21
     paradise
    1.08
     islands
    1.03
     island
    1.03
     Island
    0.96
     nation
    0.87
     Islanders
    0.87
     hopping
    0.85
     Hispan
    0.84
     Bahamas
    0.84
    Activations Density 0.043%

    No Known Activations