© 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. 7-RES-JB
    11. 23884
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, particularly those involving a specific number of hours

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "24 hours."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atown
    -1.01
    lda
    -0.92
    ovie
    -0.86
    enegger
    -0.86
     Beir
    -0.74
    icago
    -0.74
    yrim
    -0.73
    ileaks
    -0.72
    achu
    -0.72
    atchewan
    -0.69
    POSITIVE LOGITS
    00
    0.96
     hrs
    0.85
     hours
    0.85
    hours
    0.84
    teen
    0.84
    th
    0.82
     Hours
    0.81
    576
    0.80
     Hour
    0.78
    Hour
    0.77
    Activations Density 0.061%

    No Known Activations