© 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. 1-RES-JB
    11. 20317
    Prev
    Next
    INDEX
    Explanations

    specific times of day expressed in PM

    oai_token-act-pair · gpt-3.5-turbo

    time indicators in the format of "pm."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crus
    -0.81
    tymology
    -0.78
    rities
    -0.77
    quished
    -0.72
    vana
    -0.71
     Flavoring
    -0.67
    quartered
    -0.66
    bearing
    -0.64
    covered
    -0.64
    heast
    -0.63
    POSITIVE LOGITS
     pm
    1.25
    pm
    0.96
     EDT
    0.95
    PM
    0.94
    essage
    0.91
    ueller
    0.90
     EST
    0.89
    EMBER
    0.84
     ET
    0.80
     PM
    0.79
    Activations Density 0.005%

    No Known Activations