© 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. 0-RES-JB
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    references to legal courts, particularly the Supreme Court

    oai_token-act-pair · gpt-3.5-turbo

    references to the Supreme Court

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mx
    -0.67
     ESP
    -0.66
     vib
    -0.65
     RPM
    -0.63
    stretched
    -0.62
     plugged
    -0.61
     masc
    -0.61
     props
    -0.60
     nood
    -0.59
    sheets
    -0.59
    POSITIVE LOGITS
     Court
    3.80
    Court
    2.70
     COURT
    2.61
     court
    2.56
     Courts
    2.54
    court
    2.27
     courts
    1.96
     Tribunal
    1.80
     courtroom
    1.78
     Judge
    1.76
    Activations Density 0.016%

    No Known Activations