© 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 EvalsExportsinterp-engineNEWAPI 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. 3480
    Prev
    Next
    INDEX
    Explanations

    references to legal decisions or court rulings

    oai_token-act-pair · gpt-3.5-turbo

    references to legal decisions and rulings

    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
     cov
    -0.99
    ocument
    -0.89
    76561
    -0.85
    BILL
    -0.73
     pledges
    -0.71
    ontent
    -0.71
    morrow
    -0.70
     stub
    -0.69
    perture
    -0.68
    ription
    -0.68
    POSITIVE LOGITS
     Appeals
    1.39
     justices
    1.38
     appellate
    1.33
     Circuit
    1.32
     appeals
    1.30
     Ninth
    1.21
     Court
    1.18
     Supreme
    1.14
     court
    1.08
    jud
    1.06
    Activations Density 0.163%

    No Known Activations