© 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. 10-RES-JB
    11. 15996
    Prev
    Next
    INDEX
    Explanations

    instances of time-related phrases or expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "these days" and variations surrounding temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apego
    -0.61
     Chevron
    -0.61
     Uriel
    -0.59
    ilon
    -0.58
    phasis
    -0.57
     Released
    -0.57
    glass
    -0.56
    ees
    -0.54
    etics
    -0.54
    ItemTracker
    -0.53
    POSITIVE LOGITS
     mornings
    1.28
     days
    1.27
    days
    1.19
     nights
    1.18
     times
    1.16
     day
    1.13
     evenings
    1.09
     weekends
    1.08
    times
    1.06
     time
    1.05
    Activations Density 0.164%

    No Known Activations