© 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
    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. 17741
    Prev
    Next
    INDEX
    Explanations

    concepts related to time and its various expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time-related expressions or durations

    oai_token-act-pair · gpt-3.5-turbo
    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
    Downloadha
    -0.72
     newsletters
    -0.71
     Beer
    -0.71
     Freem
    -0.67
    ouls
    -0.66
     Scouting
    -0.64
    ICAN
    -0.61
     Drugs
    -0.61
     ®
    -0.61
     Printed
    -0.60
    POSITIVE LOGITS
     scheme
    1.06
     regimen
    1.05
     curve
    1.01
     regime
    0.99
     structure
    0.99
     pathway
    0.99
    base
    0.97
     pattern
    0.96
     spree
    0.96
     span
    0.95
    Activations Density 0.943%

    No Known Activations