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. 11-RES-JB
    6. 15424
    Prev
    Next
    INDEX
    Explanations

    descriptions related to tourism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tourism and visitor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.89
    esson
    -0.72
    lished
    -0.72
    ©¶æ
    -0.71
    arity
    -0.69
    SourceFile
    -0.68
    stock
    -0.67
    aucuses
    -0.64
    osi
    -0.64
    stocks
    -0.62
    POSITIVE LOGITS
     attractions
    1.22
     attraction
    1.09
     visiting
    0.96
    seeing
    0.89
     arrivals
    0.88
     destinations
    0.83
     visitors
    0.81
     flock
    0.81
     visa
    0.78
     visas
    0.77
    Activations Density 0.091%

    No Known Activations