© 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. 8-RES-JB
    11. 2577
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations, particularly islands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific islands and related terms in geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilyn
    -0.83
    baugh
    -0.79
    itbart
    -0.76
    anooga
    -0.74
    OUGH
    -0.74
    earable
    -0.72
    orr
    -0.72
    WORK
    -0.71
    IENCE
    -0.71
    kus
    -0.71
    POSITIVE LOGITS
     Islands
    1.52
     islands
    1.03
     Island
    0.88
     Peninsula
    0.85
     peninsula
    0.83
     Strait
    0.82
     Albania
    0.80
     island
    0.77
     Petroleum
    0.76
     Philippines
    0.74
    Activations Density 0.042%

    No Known Activations