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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 13611
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating timeframes or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tain
    -0.66
    ité
    -0.64
    grave
    -0.63
    eri
    -0.60
    ãģĨ
    -0.60
    arling
    -0.60
    ynasty
    -0.60
    dar
    -0.59
    adder
    -0.59
    ional
    -0.59
    POSITIVE LOGITS
     seconds
    1.21
     minutes
    1.06
     mere
    1.06
     milliseconds
    1.06
     succession
    1.02
     less
    1.00
     Seconds
    0.95
     blink
    0.94
     unison
    0.93
     fifteen
    0.92
    Activations Density 0.219%

    No Known Activations