Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11146
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Starbucks"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand Starbucks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysis
    -0.70
    uclear
    -0.69
    ologically
    -0.68
    usting
    -0.65
    avid
    -0.65
    yss
    -0.65
    otyp
    -0.65
     conting
    -0.64
    onsense
    -0.64
    othy
    -0.64
    POSITIVE LOGITS
    bucks
    0.97
     Stores
    0.87
     Coffee
    0.85
     ®
    0.84
     Restaur
    0.83
    Store
    0.82
     caf
    0.82
     cafes
    0.80
     cafe
    0.80
     Starbucks
    0.79
    Activations Density 0.010%

    No Known Activations