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. 18617
    Prev
    Next
    INDEX
    Explanations

    references to historical time periods, specifically the term "Century" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific centuries, particularly the 7th, 8th, 9th, and 10th centuries

    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
    */(
    -0.82
    gotten
    -0.75
    Contents
    -0.75
     nont
    -0.74
    ebin
    -0.74
    Marginal
    -0.74
    kell
    -0.71
    ansom
    -0.71
    ARB
    -0.71
    flows
    -0.70
    POSITIVE LOGITS
     Century
    1.52
    Cent
    0.92
     Cent
    0.89
     Millennium
    0.86
     Advantage
    0.77
     Tradition
    0.76
     Theater
    0.74
     Warfare
    0.74
     Vision
    0.74
     Meter
    0.74
    Activations Density 0.008%

    No Known Activations