© 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. 8-RES-JB
    11. 12561
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal standards and evidence evaluation

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to legal standards and reasonable doubts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.87
    paces
    -0.81
    hops
    -0.79
    lite
    -0.78
    romeda
    -0.77
    ahime
    -0.75
    nect
    -0.73
     Hispan
    -0.73
    chin
    -0.72
    ModLoader
    -0.72
    POSITIVE LOGITS
     defendant
    1.07
     Defendant
    1.05
     impairment
    1.04
     malice
    1.04
     sufficient
    1.04
     incrim
    1.01
     prejud
    1.00
     unlawful
    1.00
     harm
    0.99
     evidence
    0.99
    Activations Density 0.555%

    No Known Activations