Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2390
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases and political affairs

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain legal terminology or references to lawsuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iably
    -0.82
    NetMessage
    -0.76
     ("
    -0.74
    elvet
    -0.73
    é¾įåĸļ士
    -0.72
    ogle
    -0.68
    robe
    -0.68
    ãĢIJ
    -0.66
    ãĤ½
    -0.66
    iable
    -0.65
    POSITIVE LOGITS
     Says
    1.19
    Adds
    1.05
     warns
    1.01
     feds
    1.01
     Dems
    0.94
     predicts
    0.91
     slams
    0.87
     vows
    0.86
     Shutterstock
    0.84
     says
    0.84
    Activations Density 0.241%

    No Known Activations