© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8330
    Prev
    Next
    INDEX
    Explanations

    the word "repeatedly" followed by a verb in present tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeatedly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itarian
    -0.62
     Worth
    -0.61
    "},{"
    -0.61
     Benefit
    -0.59
     Shipping
    -0.59
     benefit
    -0.58
    fit
    -0.58
     Benefits
    -0.57
     Savings
    -0.57
    oin
    -0.57
    POSITIVE LOGITS
     repeatedly
    3.29
     forcefully
    1.83
     periodically
    1.75
     continually
    1.73
     relentlessly
    1.72
     consistently
    1.68
     continuously
    1.67
     routinely
    1.65
     frequently
    1.62
     repeated
    1.60
    Activations Density 0.018%

    No Known Activations