© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 16691
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to defamation and due process

    oai_token-act-pair · gpt-3.5-turbo

    legal concepts related to defamation and liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mond
    -0.82
     Chemistry
    -0.78
     Bild
    -0.77
     Columb
    -0.71
     indo
    -0.71
    lde
    -0.70
    hap
    -0.70
    stasy
    -0.69
     Scouting
    -0.68
    enhagen
    -0.68
    POSITIVE LOGITS
     attorney
    1.22
     attorneys
    1.16
     immunity
    1.06
     appellate
    1.01
    Attorney
    1.01
     litigation
    1.01
     sue
    1.00
     statute
    0.97
     lawyer
    0.96
     suing
    0.95
    Activations Density 0.245%

    No Known Activations