© 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. 11848
    Prev
    Next
    INDEX
    Explanations

    information related to business plans and actions, particularly in the context of tech-based services

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to regulations and compliance in the transportation industry, specifically concerning taxi services and app-based ride providers

    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
     vit
    -0.93
     Saddam
    -0.89
    assium
    -0.85
     humid
    -0.84
    NAT
    -0.82
    hiba
    -0.81
     arsen
    -0.79
     rye
    -0.79
     Iw
    -0.78
     disarm
    -0.78
    POSITIVE LOGITS
     Uber
    2.39
     Lyft
    2.27
    Uber
    2.23
     Taxi
    1.91
     taxi
    1.90
     taxis
    1.82
     rides
    1.70
     ride
    1.65
     cab
    1.50
     fares
    1.46
    Activations Density 0.235%

    No Known Activations