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. 9-RES-JB
    6. 8086
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format (e.g., "Wednesday, April 2, 2008")

    oai_token-act-pair · gpt-3.5-turbo

    specific dates or chronological information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspiration
    -0.67
     safegu
    -0.67
     recourse
    -0.66
     steering
    -0.65
     swearing
    -0.65
     numbering
    -0.65
     dissu
    -0.64
     armour
    -0.64
     upkeep
    -0.63
     supervisor
    -0.63
    POSITIVE LOGITS
    Reviewer
    1.06
    LOS
    0.99
    ³³³
    0.97
    SAN
    0.95
    PRESS
    0.95
    WASHINGTON
    0.95
    IRO
    0.93
    Posted
    0.92
    GREEN
    0.91
    PORT
    0.90
    Activations Density 0.129%

    No Known Activations