© 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. 2-RES-JB
    11. 9511
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of time, specifically mentioning hours

    oai_token-act-pair · gpt-3.5-turbo

    references to hourly time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LECT
    -0.78
    ften
    -0.64
    OTUS
    -0.64
    ortium
    -0.63
    acea
    -0.63
    ========
    -0.63
    artisan
    -0.60
    isSpecialOrderable
    -0.59
     Command
    -0.59
     Bind
    -0.59
    POSITIVE LOGITS
    endment
    1.03
    bnb
    1.00
    glass
    0.98
    istance
    0.93
     ILCS
    0.92
    hour
    0.82
    wise
    0.81
    assian
    0.80
    uty
    0.78
    ierre
    0.75
    Activations Density 0.010%

    No Known Activations