© 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. 2970
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official decisions and processes

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and concepts related to jurisdiction or legal proceedings

    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
     loves
    -0.71
     kindred
    -0.67
     Travels
    -0.67
    cyclopedia
    -0.67
     FANT
    -0.64
    ankind
    -0.64
     love
    -0.63
    Favorite
    -0.62
     descendant
    -0.60
     paradise
    -0.60
    POSITIVE LOGITS
     postp
    1.00
     delaying
    0.98
     delays
    0.97
     adjourn
    0.96
     delay
    0.95
     rescind
    0.95
     redacted
    0.94
     deadline
    0.92
     deadlines
    0.90
     waivers
    0.90
    Activations Density 1.186%

    No Known Activations