© 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. 11-RES-JB
    11. 7176
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to courts and judges

    oai_token-act-pair · gpt-3.5-turbo
    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
     srfAttach
    -0.73
    Dialogue
    -0.72
    200000
    -0.70
    76561
    -0.68
    geries
    -0.67
    ocument
    -0.65
    ggies
    -0.63
    paste
    -0.63
     Paste
    -0.62
    api
    -0.61
    POSITIVE LOGITS
     ruled
    1.45
     upheld
    1.43
     sided
    1.37
     overturned
    1.34
     rejected
    1.26
     reversed
    1.22
     granted
    1.17
     acquitted
    1.15
     halted
    1.15
     affirmed
    1.15
    Activations Density 0.100%

    No Known Activations