© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14303
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal procedures and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal procedures and the consequences of actions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    çīĪ
    -0.72
    ãĢ
    -0.63
     Verse
    -0.58
     (@
    -0.58
    ______
    -0.56
    MpServer
    -0.56
     Breakfast
    -0.56
    Cube
    -0.55
    bold
    -0.55
    luaj
    -0.54
    POSITIVE LOGITS
    usually
    1.05
     usually
    0.97
     typically
    0.93
     invariably
    0.91
    typically
    0.90
    often
    0.86
     Typically
    0.77
    depending
    0.76
     ordinarily
    0.74
     Usually
    0.73
    Activations Density 1.578%

    No Known Activations