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. 10-RES-JB
    6. 11895
    Prev
    Next
    INDEX
    Explanations

    actions related to official or legal documents being signed into law

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing laws or legislation

    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
     WATCHED
    -0.80
    asks
    -0.71
    cair
    -0.64
    cation
    -0.64
    entimes
    -0.63
    yip
    -0.61
    rera
    -0.58
     lured
    -0.58
    gets
    -0.58
    ocus
    -0.57
    POSITIVE LOGITS
     law
    1.09
     effect
    0.97
     statute
    0.92
     existence
    0.87
    Effective
    0.80
     legislation
    0.79
     fruition
    0.78
     statutes
    0.75
     Law
    0.73
    aug
    0.71
    Activations Density 0.080%

    No Known Activations