© 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. 9-RES-JB
    11. 11295
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation infrastructure and planning

    oai_token-act-pair · gpt-3.5-turbo

    references to pedestrian and cycling infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.95
     Illuminati
    -0.88
     Witch
    -0.88
    secret
    -0.87
     Schwar
    -0.85
    Secret
    -0.82
     witch
    -0.81
     Primordial
    -0.76
     Seth
    -0.75
     neocons
    -0.75
    POSITIVE LOGITS
     pedestrians
    1.78
     motorists
    1.61
     pedestrian
    1.61
     commuters
    1.60
     taxis
    1.59
     commuting
    1.59
     buses
    1.56
     commuter
    1.54
     commute
    1.52
     traffic
    1.52
    Activations Density 1.141%

    No Known Activations