© 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. 4-RES-JB
    11. 20893
    Prev
    Next
    INDEX
    Explanations

    specific mentions of time frames related to weeks during different life events

    oai_token-act-pair · gpt-3.5-turbo

    references to weeks of gestation and pregnancy duration

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

    No Comments

    Negative Logits
    inav
    -0.80
    cellence
    -0.69
    Reviewer
    -0.68
    ifice
    -0.67
    backer
    -0.65
    ech
    -0.63
    emort
    -0.62
    acted
    -0.61
     Crunch
    -0.61
     CSI
    -0.61
    POSITIVE LOGITS
    days
    1.08
     ago
    1.05
     Ago
    0.91
     gestation
    0.87
    DAY
    0.85
    iversary
    0.80
    assetsadobe
    0.79
    oldown
    0.78
    pring
    0.75
    ²¾
    0.75
    Activations Density 0.036%

    No Known Activations