© 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. 11-RES-JB
    11. 22138
    Prev
    Next
    INDEX
    Explanations

    time-related information, specifically hours of operation and schedules

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to time and scheduling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROM
    -0.74
    DI
    -0.68
    LG
    -0.67
    harm
    -0.65
    Fran
    -0.64
    has
    -0.63
    isations
    -0.63
    Gar
    -0.63
    IGN
    -0.63
    versions
    -0.63
    POSITIVE LOGITS
     p
    1.49
     pm
    1.09
     noon
    1.03
     pp
    0.94
     midnight
    0.90
     pa
    0.87
    p
    0.83
     ping
    0.82
     pt
    0.81
     o
    0.79
    Activations Density 0.033%

    No Known Activations