© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17608
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical structures such as bridges

    oai_token-act-pair · gpt-3.5-turbo

    references to various bridges and bridge-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arily
    -0.78
    matically
    -0.73
    iaries
    -0.66
    ij士
    -0.66
    atically
    -0.65
    ccording
    -0.63
    ²
    -0.62
    ISTER
    -0.62
    eal
    -0.62
    psy
    -0.62
    POSITIVE LOGITS
     Strait
    0.95
    port
    0.94
    bridge
    0.87
    roads
    0.87
     bridge
    0.85
    layer
    0.84
     bridges
    0.84
    yard
    0.81
     Simulator
    0.81
     Bridges
    0.81
    Activations Density 0.039%

    No Known Activations