© 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 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. 10-RES-JB
    11. 16596
    Prev
    Next
    INDEX
    Explanations

    phrases indicating passage or change occurring over time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of time and its progression or changes

    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
    VK
    -0.81
    emis
    -0.74
    ursday
    -0.69
    Sys
    -0.66
    uala
    -0.65
     Yesterday
    -0.64
    pload
    -0.63
    Els
    -0.61
    itialized
    -0.60
     Moons
    -0.60
    POSITIVE LOGITS
    Footnote
    0.83
    .
    0.69
    deals
    0.68
     depending
    0.65
    idth
    0.65
     partName
    0.65
    ;
    0.63
     diminishing
    0.61
    adjust
    0.60
    forward
    0.58
    Activations Density 0.195%

    No Known Activations