© 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. 8-RES-JB
    11. 17798
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take care."

    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
    coni
    -0.65
    Kings
    -0.58
     Chili
    -0.58
     rage
    -0.56
    ipl
    -0.56
    ICAN
    -0.56
    KEN
    -0.55
     veins
    -0.55
     erupt
    -0.54
     eru
    -0.54
    POSITIVE LOGITS
    taker
    1.14
    giving
    0.89
    tesy
    0.80
    fully
    0.78
    ktop
    0.75
     âĶľ
    0.73
     largeDownload
    0.72
    ful
    0.72
    taking
    0.72
     respecting
    0.70
    Activations Density 0.016%

    No Known Activations