© 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 EvalsExportsinterp-engineNEWAPI 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. 14079
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a specific time or context related to an event

    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
    ants
    -0.62
    burn
    -0.59
    olves
    -0.58
    #$
    -0.58
    oub
    -0.57
    hunt
    -0.56
    orde
    -0.54
    oke
    -0.54
     Stream
    -0.53
    obar
    -0.53
    POSITIVE LOGITS
     time
    2.46
    time
    1.96
     times
    1.67
     day
    1.62
     Time
    1.58
     TIME
    1.54
    Time
    1.52
    times
    1.42
     moment
    1.36
    TIME
    1.29
    Activations Density 0.611%

    No Known Activations