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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 8387
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and guidelines

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.77
    oyal
    -0.73
    naissance
    -0.71
     ful
    -0.68
     Ascension
    -0.67
     sleeper
    -0.64
    culus
    -0.63
     cardio
    -0.63
     sensations
    -0.63
    Rus
    -0.63
    POSITIVE LOGITS
    enforcement
    1.27
     enforced
    1.20
     prohibiting
    1.11
     enforce
    1.09
     regulating
    1.08
     enacted
    1.08
     regulations
    1.06
     loopholes
    1.06
     governs
    1.05
     stricter
    1.03
    Activations Density 0.567%

    No Known Activations