© 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. 4391
    Prev
    Next
    INDEX
    Explanations

    relevant to legal and judicial matters

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

    legal terms and phrases related to court rulings and constitutional rights

    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
     Massive
    -0.73
     Finish
    -0.65
     Reboot
    -0.65
     Lonely
    -0.65
     Alps
    -0.63
     Tropical
    -0.61
     favourite
    -0.61
     Seasons
    -0.61
     Wander
    -0.60
    usterity
    -0.60
    POSITIVE LOGITS
     pursuant
    1.24
     Plaint
    1.16
     plaintiff
    1.13
     appellant
    1.10
     Plaintiff
    1.08
     petitioner
    1.08
     plaintiffs
    1.04
     âĢ
    1.02
     defendant
    1.01
     Defendant
    1.01
    Activations Density 0.594%

    No Known Activations