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. 1-RES-JB
    6. 6306
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and legal processes

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to legislative processes and ballot measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tur
    -0.80
     Kut
    -0.71
    vity
    -0.70
    ãĤ¨ãĥ«
    -0.68
    ographies
    -0.68
    Series
    -0.68
    links
    -0.68
    Naz
    -0.67
    vantage
    -0.67
    Images
    -0.66
    POSITIVE LOGITS
     legalizing
    1.28
     decriminal
    1.21
     ratified
    1.07
     legalized
    1.06
     ratification
    1.04
     authorizing
    1.02
     regulating
    1.01
     repealing
    0.98
     unanimously
    0.96
     legisl
    0.90
    Activations Density 0.248%

    No Known Activations