© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    specific time-related phrases and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to timing and specificity

    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
    inis
    -0.69
    inav
    -0.65
    Better
    -0.64
    uphem
    -0.62
    ionics
    -0.62
    Built
    -0.61
    ukemia
    -0.61
    ordes
    -0.61
    packages
    -0.61
    athing
    -0.60
    POSITIVE LOGITS
     time
    1.41
     moment
    1.35
     times
    1.34
     jun
    1.32
     point
    1.26
     location
    1.19
     intervals
    1.11
     stage
    1.10
     moments
    1.05
     locations
    1.03
    Activations Density 0.108%

    No Known Activations