© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8374
    Prev
    Next
    INDEX
    Explanations

    mentions of the ridesharing companies Uber and Lyft

    oai_token-act-pair · gpt-3.5-turbo

    references to ride-sharing services, particularly Lyft

    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
    orescent
    -0.82
    ourning
    -0.81
    umar
    -0.80
    anamo
    -0.78
    thur
    -0.78
    unta
    -0.77
    urity
    -0.75
    urally
    -0.75
    manuel
    -0.72
    pex
    -0.72
    POSITIVE LOGITS
     Lyft
    0.99
     Chaser
    0.80
     rides
    0.74
     Riders
    0.67
    Dash
    0.65
     squee
    0.62
     Drivers
    0.62
     Lilly
    0.61
     Companion
    0.61
     Compan
    0.60
    Activations Density 0.012%

    No Known Activations