© 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. 11-RES-JB
    11. 20635
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a passage of time

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "over the past year."

    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
    vu
    -0.77
    ept
    -0.76
    itaire
    -0.75
    oka
    -0.73
    itia
    -0.73
    uala
    -0.71
    chy
    -0.69
    enf
    -0.68
    istry
    -0.68
    fully
    -0.66
    POSITIVE LOGITS
     course
    1.43
     weekend
    1.34
     past
    1.28
     objections
    1.15
     years
    1.14
     span
    1.11
     holidays
    1.11
     ensuing
    1.06
     next
    1.05
     last
    1.03
    Activations Density 0.041%

    No Known Activations