© 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. 11-RES-JB
    11. 24504
    Prev
    Next
    INDEX
    Explanations

    mentions of the U.S. 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gobl
    -0.75
     pus
    -0.74
    76561
    -0.68
     stub
    -0.68
    OPLE
    -0.65
     bins
    -0.63
    ppo
    -0.62
     tremend
    -0.62
     prone
    -0.61
    ickr
    -0.60
    POSITIVE LOGITS
     Court
    1.61
    Court
    1.21
     Judicial
    1.11
     Courts
    1.07
     Ct
    1.05
    court
    1.01
     Tribunal
    0.99
     court
    0.94
     justices
    0.93
     COURT
    0.89
    Activations Density 0.012%

    No Known Activations