© 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. 9-RES-JB
    11. 20684
    Prev
    Next
    INDEX
    Explanations

    instances of time frames, specifically focusing on durations of 24 hours

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "24 hours" or any time-related 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
    lda
    -0.99
    atown
    -0.95
    enegger
    -0.85
    ovie
    -0.77
    andise
    -0.69
     Beir
    -0.66
    iewicz
    -0.66
    achu
    -0.65
     Gemini
    -0.65
     Tate
    -0.65
    POSITIVE LOGITS
     hrs
    0.95
    hours
    0.94
    00
    0.93
     Hours
    0.93
     hours
    0.90
    teen
    0.90
     Sussex
    0.89
     Hour
    0.83
    576
    0.80
    Hour
    0.79
    Activations Density 0.097%

    No Known Activations