© 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. 1-RES-JB
    11. 22677
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court decisions

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to court decisions and rulings

    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
    lasses
    -0.67
     Zi
    -0.67
    ycle
    -0.66
    ococ
    -0.65
    urses
    -0.65
    icro
    -0.64
    ription
    -0.63
    roots
    -0.62
    ults
    -0.62
     Thy
    -0.61
    POSITIVE LOGITS
     rulings
    1.01
    sup
    0.94
     justices
    0.89
    Reviewed
    0.87
     upholding
    0.84
     Scalia
    0.84
    iff
    0.83
     ruling
    0.82
     precedent
    0.79
    Attorney
    0.79
    Activations Density 0.153%

    No Known Activations