© 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. 7407
    Prev
    Next
    INDEX
    Explanations

    text related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    negative numerical values associated with durations or time spans

    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
     Rica
    -0.75
     Dos
    -0.66
     Mara
    -0.64
     heights
    -0.64
     Thumbnails
    -0.64
     Illum
    -0.64
     Uncle
    -0.63
     Proc
    -0.63
     Glas
    -0.63
     Borders
    -0.63
    POSITIVE LOGITS
    minute
    1.46
    year
    1.46
    month
    1.43
    hour
    1.43
    million
    1.34
    member
    1.29
    second
    1.29
    mile
    1.28
    degree
    1.27
    percent
    1.26
    Activations Density 0.079%

    No Known Activations