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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 8320
    Prev
    Next
    INDEX
    Explanations

    phrases related to buses

    oai_token-act-pair · gpt-3.5-turbo

    references to buses, particularly the "Bus" entity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appraisal
    -0.71
    amorph
    -0.66
     coral
    -0.66
     titanium
    -0.63
    encer
    -0.63
     concerns
    -0.63
     karma
    -0.63
     mercury
    -0.63
    ovember
    -0.63
     calcium
    -0.62
    POSITIVE LOGITS
     Bus
    3.97
    Bus
    2.95
     bus
    2.06
     BUS
    1.85
    bus
    1.82
     buses
    1.63
    BUS
    1.48
     Boat
    1.32
     Shuttle
    1.26
     Truck
    1.11
    Activations Density 0.015%

    No Known Activations