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. 2-RES-JB
    6. 4991
    Prev
    Next
    INDEX
    Explanations

    references to the passing of bills or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bills and their passage through government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carnage
    -0.78
    cult
    -0.72
     rumours
    -0.68
    arna
    -0.67
     vantage
    -0.67
     Dh
    -0.67
    Asia
    -0.65
     realise
    -0.65
     Pent
    -0.64
    ihad
    -0.64
    POSITIVE LOGITS
     defund
    1.00
     legislative
    0.99
     legisl
    0.99
     legalizing
    0.97
     repeal
    0.97
     legalized
    0.94
     Legislature
    0.92
     legislation
    0.92
     bipartisan
    0.92
     repealing
    0.91
    Activations Density 0.860%

    No Known Activations