© 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. 12-RES-JB
    11. 3707
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate properties and urban development projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to urban development and community infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    othal
    -0.92
    ouble
    -0.85
    idav
    -0.79
    DK
    -0.75
    ebted
    -0.75
    EStream
    -0.75
    éŃĶ
    -0.74
    Tracker
    -0.72
     Daughter
    -0.71
    Brother
    -0.70
    POSITIVE LOGITS
     sidewalks
    1.55
     amenities
    1.54
     pedestrian
    1.41
     amen
    1.37
     parking
    1.33
     entrances
    1.30
     sidewalk
    1.27
     veh
    1.24
     pedestrians
    1.23
     landsc
    1.22
    Activations Density 0.340%

    No Known Activations