© 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. 20349
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and verdicts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal judgments and issues of guilt or innocence

    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
    opian
    -0.67
    Hop
    -0.67
    ummer
    -0.65
     learners
    -0.63
    inson
    -0.63
    urgical
    -0.63
    ctl
    -0.63
     visitors
    -0.62
    birth
    -0.61
    rish
    -0.60
    POSITIVE LOGITS
     innocence
    0.92
     Prosecutors
    0.88
     exoner
    0.85
     indict
    0.83
     verdict
    0.83
     accused
    0.82
    Prosecut
    0.81
     perjury
    0.80
     incrim
    0.79
    icate
    0.79
    Activations Density 0.149%

    No Known Activations