© 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. 8-RES-JB
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or events related to a specific duration or period of time

    oai_token-act-pair · gpt-3.5-turbo

    references to time spans, particularly years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ment
    -0.70
    dinand
    -0.67
    omething
    -0.66
    ":[{"
    -0.66
    cius
    -0.63
    rox
    -0.62
    rior
    -0.62
     intermedi
    -0.61
    anson
    -0.61
    owsky
    -0.61
    POSITIVE LOGITS
     opener
    0.63
    BY
    0.63
    forth
    0.61
     since
    0.60
     scrimmage
    0.60
     resurg
    0.59
    äº
    0.59
    opening
    0.59
     Copyright
    0.59
     Spr
    0.56
    Activations Density 0.098%

    No Known Activations