© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    locations and routes related to transportation and trade

    oai_token-act-pair · gpt-3.5-turbo

    references to various transportation and trade routes

    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
     Darrell
    -0.80
    ancies
    -0.79
     cand
    -0.76
    lik
    -0.64
     Horowitz
    -0.64
    reenshots
    -0.64
     Lerner
    -0.63
    ovember
    -0.62
     makeup
    -0.61
     Tsukuyomi
    -0.60
    POSITIVE LOGITS
     routes
    1.32
     transporting
    1.18
     ferry
    1.16
    route
    1.14
     route
    1.13
     flights
    1.07
     Strait
    1.05
     ports
    1.03
     cables
    1.03
     transports
    1.02
    Activations Density 0.747%

    No Known Activations