Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 22032
    Prev
    Next
    INDEX
    Explanations

    references to specific centuries, particularly the 20th century

    oai_token-act-pair · gpt-3.5-turbo

    references to different centuries, particularly the 20th and 21st

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.89
    toc
    -0.89
    itely
    -0.88
    ebin
    -0.87
    DAQ
    -0.85
    Marginal
    -0.84
    haps
    -0.84
    ractive
    -0.81
    ached
    -0.75
    gotten
    -0.75
    POSITIVE LOGITS
     Century
    1.25
     Cent
    0.84
     Millennium
    0.83
     Falcon
    0.80
     Fox
    0.78
     Leap
    0.76
     Struggle
    0.75
     Actress
    0.75
     Fighter
    0.74
    aire
    0.73
    Activations Density 0.011%

    No Known Activations