© 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. 5715
    Prev
    Next
    INDEX
    Explanations

    phrases related to frequency and recurring actions

    oai_token-act-pair · gpt-3.5-turbo

    references to frequency and duration of occurrences, specifically "case-by-case" or "daily" references

    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
     exits
    -0.81
    dogs
    -0.81
    tests
    -0.78
    hops
    -0.77
    ushes
    -0.75
     Tears
    -0.73
    abies
    -0.73
     Answers
    -0.73
    stories
    -0.73
    doors
    -0.72
    POSITIVE LOGITS
     basis
    2.23
     scale
    1.40
     footing
    1.34
     level
    1.19
     whim
    1.10
     timetable
    1.07
     trajectory
    1.05
     occasion
    1.03
     wavelength
    1.00
     dime
    1.00
    Activations Density 0.081%

    No Known Activations