© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9928
    Prev
    Next
    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or changes in time

    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
     someday
    -0.78
     nowadays
    -0.74
    2006
    -0.65
     lately
    -0.61
     recently
    -0.61
     2006
    -0.58
    )[
    -0.57
    2007
    -0.57
    )]
    -0.57
    Years
    -0.57
    POSITIVE LOGITS
     anew
    0.92
    again
    0.89
     again
    0.88
     refreshed
    0.75
    irming
    0.65
    amiliar
    0.64
     Again
    0.63
     reminder
    0.63
     anx
    0.62
     scramble
    0.62
    Activations Density 1.129%

    No Known Activations