© 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. 3-RES-JB
    11. 20634
    Prev
    Next
    INDEX
    Explanations

    words related to refreshing or updating something, such as cache, webpage, or memory

    oai_token-act-pair · gpt-3.5-turbo

    terms related to refreshing or renewal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jun
    -0.73
    nuclear
    -0.71
    HO
    -0.69
    SHIP
    -0.69
    GO
    -0.69
    MET
    -0.67
    IP
    -0.66
    Church
    -0.65
    CHO
    -0.64
    Leary
    -0.64
    POSITIVE LOGITS
     refresh
    1.25
    issance
    1.17
     Refresh
    1.13
     refres
    1.11
     refreshed
    1.05
    ments
    0.89
    ements
    0.82
    mentation
    0.82
    itial
    0.80
     recapt
    0.77
    Activations Density 0.007%

    No Known Activations