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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 6116
    Prev
    Next
    INDEX
    Explanations

    mentions of legal institutions, specifically the Supreme Court

    oai_token-act-pair · gpt-3.5-turbo

    references to the Supreme Court and its decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ku
    -0.83
    ptoms
    -0.82
    ãĤ¨ãĥ«
    -0.78
    eworld
    -0.71
    river
    -0.70
    ufact
    -0.69
    ombies
    -0.68
    ontent
    -0.68
    resp
    -0.66
    Redd
    -0.65
    POSITIVE LOGITS
     justices
    1.32
     Justice
    1.02
    Justice
    0.95
     rulings
    0.94
     Judicial
    0.86
     ruling
    0.85
     nominee
    0.84
     upheld
    0.83
     Court
    0.80
     vacancy
    0.80
    Activations Density 0.052%

    No Known Activations