© 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. 9-RES-JB
    11. 15763
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, specifically durations like days, years, hours, and months

    oai_token-act-pair · gpt-3.5-turbo

    time-related quantities and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãĥķãĤ©
    -0.66
    irie
    -0.66
     hypocr
    -0.65
     defe
    -0.63
     colle
    -0.59
    amara
    -0.56
     Punk
    -0.54
    gotten
    -0.54
     failings
    -0.54
    SHARE
    -0.53
    POSITIVE LOGITS
     intervals
    1.15
     increments
    1.12
     depending
    1.02
    depending
    1.00
     duration
    1.00
     elapsed
    1.00
     ago
    0.97
     apiece
    0.94
     consecut
    0.91
     periods
    0.90
    Activations Density 0.138%

    No Known Activations