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. 15096
    Prev
    Next
    INDEX
    Explanations

    terms related to ridesharing services, specifically highlighting mentions of the company "Uber."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rideshare companies, particularly Uber and Lyft

    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
    adow
    -0.76
    vere
    -0.74
    warts
    -0.73
    èª
    -0.71
    orial
    -0.69
    LECT
    -0.69
    lder
    -0.68
    archives
    -0.67
    udic
    -0.66
    acular
    -0.66
    POSITIVE LOGITS
    Uber
    0.93
     Uber
    0.93
    mens
    0.87
     Lyft
    0.86
    lane
    0.81
    Pool
    0.78
    enhagen
    0.74
     taxis
    0.71
     resil
    0.71
    riages
    0.66
    Activations Density 0.010%

    No Known Activations