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. 2-RES-JB
    6. 20150
    Prev
    Next
    INDEX
    Explanations

    mentions of popular soda brands, particularly Coca-Cola and Pepsi

    oai_token-act-pair · gpt-3.5-turbo

    brands of soft drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittance
    -0.74
    yrim
    -0.73
    urnal
    -0.66
     rapt
    -0.66
     Locked
    -0.64
    ebin
    -0.63
    pmwiki
    -0.63
     hrs
    -0.62
    olulu
    -0.62
    seeing
    -0.62
    POSITIVE LOGITS
    Cola
    1.73
     Coke
    1.35
     Coca
    1.16
     Pepsi
    1.07
     Bottle
    1.04
     bottle
    0.92
    Bott
    0.91
     soda
    0.89
    wagon
    0.89
    weed
    0.87
    Activations Density 0.006%

    No Known Activations