© 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. 10-RES-JB
    11. 18961
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or establishments, particularly ones related to business or community activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or establishments, particularly with the word "Back."

    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
    BILITY
    -0.80
     exception
    -0.73
     quo
    -0.71
     proposition
    -0.68
     grace
    -0.68
     liability
    -0.66
     tail
    -0.66
     clock
    -0.65
     standoff
    -0.65
     consistency
    -0.64
    POSITIVE LOGITS
    Street
    1.09
    Care
    0.97
    Nation
    0.95
    Works
    0.92
    Aren
    0.92
    better
    0.90
    Aid
    0.90
    Gear
    0.90
     Designs
    0.90
     Against
    0.90
    Activations Density 0.126%

    No Known Activations