© 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. 10-RES-JB
    11. 23481
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high degree of something happening or being done

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of maximizing or minimizing something as much as possible

    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
    masters
    -0.67
    ¡
    -0.66
    eries
    -0.66
    riad
    -0.64
    mans
    -0.62
     Vish
    -0.62
    Ń
    -0.62
    ĺħ
    -0.62
    rets
    -0.61
    ª
    -0.61
    POSITIVE LOGITS
     before
    0.72
     without
    0.71
     beforehand
    0.68
    iary
    0.68
    .
    0.67
    .","
    0.66
     BEFORE
    0.66
     during
    0.65
     lest
    0.65
    uchin
    0.63
    Activations Density 0.042%

    No Known Activations