© 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. 18988
    Prev
    Next
    INDEX
    Explanations

    legal terms and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal decisions and appeals

    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
     imitation
    -0.80
     stereotype
    -0.75
     dens
    -0.72
     glor
    -0.72
     masculinity
    -0.71
     domest
    -0.70
     pim
    -0.67
     metic
    -0.67
     symb
    -0.67
     robberies
    -0.66
    POSITIVE LOGITS
     adjourn
    1.43
     pending
    1.27
     appellate
    1.22
    Attorney
    1.20
    Judge
    1.09
     deadline
    1.09
     Appeals
    1.03
     awaiting
    1.00
     Judicial
    1.00
     awaits
    0.98
    Activations Density 0.624%

    No Known Activations