© 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. 10-RES-JB
    11. 10168
    Prev
    Next
    INDEX
    Explanations

    instances related to pedestrian activities and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pedestrian activities and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mable
    -0.87
    temp
    -0.84
     marrow
    -0.81
    ģĸ
    -0.70
    outube
    -0.69
     Centauri
    -0.66
    hot
    -0.66
    zona
    -0.66
     Pharma
    -0.65
     PowerPoint
    -0.64
    POSITIVE LOGITS
     pedestrians
    1.22
     crossing
    1.04
     crossings
    1.00
     pedestrian
    0.99
     bicycl
    0.92
     sidewalk
    0.91
     jog
    0.90
     traffic
    0.87
     sidewalks
    0.87
     obstruction
    0.86
    Activations Density 0.033%

    No Known Activations