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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 20153
    Prev
    Next
    INDEX
    Explanations

    references to bus-related activities or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to buses and related terminology

    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
     attest
    -0.76
     Kelvin
    -0.71
     SEAL
    -0.70
     adjustment
    -0.63
     SG
    -0.63
     justice
    -0.62
     steroids
    -0.61
     reward
    -0.61
     reversal
    -0.61
     customization
    -0.60
    POSITIVE LOGITS
    bus
    4.60
    Bus
    2.48
    BUS
    2.24
     BUS
    1.48
     bus
    1.42
     Bus
    1.40
    abus
    1.28
     buses
    1.20
    bush
    1.12
    ibus
    1.08
    Activations Density 0.010%

    No Known Activations