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. 1-RES-JB
    6. 19787
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations in the Caribbean

    oai_token-act-pair · gpt-3.5-turbo

    references to the Caribbean region and its associated islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chen
    -0.91
    efer
    -0.86
    imen
    -0.85
    ERAL
    -0.81
    imens
    -0.80
    eral
    -0.80
    ivities
    -0.78
    vation
    -0.77
    baugh
    -0.76
    chers
    -0.75
    POSITIVE LOGITS
     Caribbean
    1.22
     Islands
    0.89
     islands
    0.81
     Cruise
    0.81
     Coast
    0.78
     Isles
    0.77
     Coastal
    0.76
     seaf
    0.76
     Indies
    0.76
     Basin
    0.75
    Activations Density 0.006%

    No Known Activations