© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods such as "the past few days" or "the past few months"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the past few" in various contexts

    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
    NP
    -0.67
     destro
    -0.65
    ibel
    -0.65
    gow
    -0.64
    obal
    -0.64
    fan
    -0.62
    enegger
    -0.61
    rawdownloadcloneembedreportprint
    -0.61
    âĶģ
    -0.60
    obar
    -0.60
    POSITIVE LOGITS
     weeks
    1.80
     months
    1.74
     years
    1.59
     days
    1.57
     decades
    1.42
    months
    1.42
     hours
    1.37
     minutes
    1.31
    years
    1.29
     nights
    1.29
    Activations Density 0.061%

    No Known Activations