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. 4-RES-JB
    6. 22894
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Starbucks"

    oai_token-act-pair · gpt-3.5-turbo

    references to Starbucks and related entities

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

    No Comments

    Negative Logits
    uclear
    -0.70
     conting
    -0.66
    avid
    -0.65
    matter
    -0.64
    ysis
    -0.63
    onsense
    -0.62
     marrow
    -0.62
    ologically
    -0.62
    Reviewer
    -0.62
     Rutherford
    -0.61
    POSITIVE LOGITS
    bucks
    0.91
     Stores
    0.87
     cafe
    0.86
     caf
    0.86
     Restaur
    0.85
    Store
    0.84
     Coffee
    0.84
     cafes
    0.84
     Starbucks
    0.82
     café
    0.82
    Activations Density 0.007%

    No Known Activations