© 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. 4-RES-JB
    11. 9423
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to court-related matters

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial institutions and legal entities

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

    No Comments

    Negative Logits
     fame
    -0.71
     ç¥ŀ
    -0.63
    ĪĴ
    -0.62
     vain
    -0.61
    ĻĤ
    -0.59
     muff
    -0.59
    ãĥķãĤ©
    -0.58
    é¾į
    -0.58
    ashes
    -0.58
     ($)
    -0.58
    POSITIVE LOGITS
    intern
    0.75
    osaurus
    0.71
     Clause
    0.68
     Term
    0.68
    itech
    0.67
     Room
    0.63
    isphere
    0.62
    Bank
    0.62
     Intellectual
    0.62
     Wars
    0.62
    Activations Density 0.160%

    No Known Activations