© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    specific time references mentioned in Eastern Time (ET)

    oai_token-act-pair · gpt-3.5-turbo

    time zone abbreviations associated with Eastern Time (ET) and Pacific Time (PT)

    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
     resemb
    -0.73
    ffield
    -0.66
     Mechdragon
    -0.63
     bushes
    -0.63
    module
    -0.61
    conservancy
    -0.61
    loads
    -0.60
    lda
    -0.60
    wagen
    -0.58
     psychologists
    -0.57
    POSITIVE LOGITS
    DAQ
    0.90
    ACH
    0.88
     ET
    0.88
    ember
    0.86
     EDT
    0.85
     Thurs
    0.84
    EMBER
    0.82
    aturdays
    0.78
    ICAN
    0.78
    uesday
    0.77
    Activations Density 0.025%

    No Known Activations