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. 6-RES-JB
    6. 8214
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative processes and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    articles or determiners, particularly the word "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !/
    -0.81
    Contents
    -0.78
    Joined
    -0.76
     somet
    -0.70
    Enjoy
    -0.68
    Arcade
    -0.68
    casts
    -0.67
    Frames
    -0.67
    âĿ
    -0.67
    ogi
    -0.67
    POSITIVE LOGITS
     comprehensive
    1.05
     bipartisan
    1.00
     plethora
    0.97
     lengthy
    0.97
     slew
    0.96
     forthcoming
    0.95
     timetable
    0.92
     referendum
    0.92
     landmark
    0.92
     federal
    0.91
    Activations Density 0.657%

    No Known Activations