© 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. 10-RES-JB
    11. 18955
    Prev
    Next
    INDEX
    Explanations

    phrases related to both past and present

    oai_token-act-pair · gpt-3.5-turbo

    references to past and present relationships or events

    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
    ooth
    -0.72
    gob
    -0.70
    EMS
    -0.65
    padding
    -0.65
    cht
    -0.63
    ationally
    -0.63
    wire
    -0.62
    gee
    -0.62
     Scrib
    -0.61
    antry
    -0.61
    POSITIVE LOGITS
     present
    1.43
     future
    1.38
     Present
    1.29
    future
    1.28
     current
    1.24
    present
    1.19
     contemporary
    1.17
    Present
    1.13
     Future
    1.09
    Future
    1.06
    Activations Density 0.193%

    No Known Activations