© 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. 4268
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and diseases

    oai_token-act-pair · gpt-3.5-turbo

    punctuated transitions or separations in thoughts and sections

    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
    rad
    -0.71
    ãĥĺ
    -0.63
    naissance
    -0.62
    andom
    -0.61
     footing
    -0.60
    minist
    -0.59
    cept
    -0.59
    cells
    -0.57
    commun
    -0.56
    bourg
    -0.56
    POSITIVE LOGITS
    hma
    0.68
    ³³³
    0.64
    ³³³³
    0.63
    PHOTOS
    0.63
     VIDEOS
    0.61
     Imran
    0.61
     Related
    0.58
    patrick
    0.56
    Meanwhile
    0.55
    Furthermore
    0.55
    Activations Density 0.434%

    No Known Activations