© 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. 3-RES-JB
    11. 20645
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal verdicts and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heritage
    -0.80
     Dak
    -0.65
    href
    -0.64
    cession
    -0.63
    ohyd
    -0.61
    abb
    -0.60
    olen
    -0.60
     Adventures
    -0.59
     Habit
    -0.59
    ris
    -0.59
    POSITIVE LOGITS
     verdict
    1.18
    ysis
    0.96
    naire
    0.95
     Judgment
    0.85
     judgement
    0.84
     judgment
    0.83
    INAL
    0.79
     debtor
    0.75
    -+-+
    0.74
     jury
    0.73
    Activations Density 0.010%

    No Known Activations