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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 23383
    Prev
    Next
    INDEX
    Explanations

    names related to legal cases, possibly involving a person named Ginsburg

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Ginsburg" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unnamed
    -0.76
     Bristol
    -0.75
     Riyadh
    -0.70
     Stamford
    -0.67
    à¤
    -0.66
     Burlington
    -0.64
     Lisbon
    -0.63
     NCT
    -0.62
     Independent
    -0.61
     firm
    -0.60
    POSITIVE LOGITS
     Gins
    1.33
    berg
    0.98
    burg
    0.98
    stein
    0.96
    haw
    0.92
    creen
    0.88
    burgh
    0.86
    erman
    0.84
    hee
    0.84
    beck
    0.83
    Activations Density 0.009%

    No Known Activations