© 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. 8-RES-JB
    11. 6329
    Prev
    Next
    INDEX
    Explanations

    statements, claims, and descriptions in legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal proceedings and criminal justice

    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
     ç¥ŀ
    -0.83
     [|
    -0.80
    Japan
    -0.78
    opter
    -0.74
    osphere
    -0.74
    Tumblr
    -0.73
    Flickr
    -0.72
     Entreprene
    -0.71
     âĺ
    -0.71
    Japanese
    -0.70
    POSITIVE LOGITS
     prosecutors
    1.41
     jurors
    1.37
     prosecutor
    1.36
     perjury
    1.35
     defendant
    1.31
    Prosecutors
    1.29
     defendants
    1.27
     prosecution
    1.25
     testified
    1.24
     detectives
    1.22
    Activations Density 1.445%

    No Known Activations