© 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. 4-RES-JB
    11. 10562
    Prev
    Next
    INDEX
    Explanations

    mentions of things making a comeback

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comeback."

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

    No Comments

    Negative Logits
    tein
    -1.08
    avery
    -0.85
    Irish
    -0.72
    ģ
    -0.72
    aves
    -0.71
    bis
    -0.70
    acht
    -0.70
    agram
    -0.66
    ETA
    -0.65
    autical
    -0.65
    POSITIVE LOGITS
     comeback
    1.09
    wcs
    0.82
     shenan
    0.71
    spective
    0.71
    ilee
    0.70
     resurgence
    0.69
    roads
    0.66
    prise
    0.66
    ilitation
    0.65
    ilitating
    0.65
    Activations Density 0.013%

    No Known Activations