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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14367
    Prev
    Next
    INDEX
    Explanations

    references to transportation and traffic-related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to traffic and transportation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.89
    Truth
    -0.79
    milo
    -0.78
    acus
    -0.78
    iasco
    -0.77
     à¤
    -0.74
    terms
    -0.74
    ername
    -0.73
    Downloadha
    -0.73
    tone
    -0.72
    POSITIVE LOGITS
     pedestrians
    1.80
     visitors
    1.68
     tourists
    1.67
     commuters
    1.58
     travelers
    1.54
     pilgrims
    1.51
     motorists
    1.49
     hikers
    1.44
     veh
    1.44
     passengers
    1.43
    Activations Density 0.382%

    No Known Activations