© 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 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. 16115
    Prev
    Next
    INDEX
    Explanations

    legal and courtroom-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal evidence and testimonies in a trial context

    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
    umbai
    -0.95
     [|
    -0.91
    Tumblr
    -0.85
    inav
    -0.85
    Saharan
    -0.81
    ghai
    -0.80
     CentOS
    -0.79
    apore
    -0.79
    ãĤ¦
    -0.78
     Entreprene
    -0.78
    POSITIVE LOGITS
     jurors
    1.92
     defendant
    1.52
     prosecutors
    1.47
     defendants
    1.47
     prosecutor
    1.44
     perjury
    1.43
     jury
    1.42
     testified
    1.41
    Prosecut
    1.39
     testimony
    1.36
    Activations Density 0.845%

    No Known Activations