© 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. 8-RES-JB
    11. 1207
    Prev
    Next
    INDEX
    Explanations

    phrases related to catching up or being up-to-date

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "catch up"

    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
     quir
    -0.67
     bil
    -0.67
     nomine
    -0.65
    gh
    -0.61
     Canaveral
    -0.61
    eln
    -0.60
    asus
    -0.60
    oway
    -0.60
    qqa
    -0.59
     goose
    -0.59
    POSITIVE LOGITS
    Notes
    0.79
    lines
    0.71
    dates
    0.70
    ancy
    0.69
    shift
    0.68
    grades
    0.68
    table
    0.67
    line
    0.66
    EDIT
    0.66
    itional
    0.66
    Activations Density 0.027%

    No Known Activations