© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    words related to medical symptoms and treatments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "umm" and related phonetic sounds, indicating hesitation or uncertainty

    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
    redo
    -0.87
    lasses
    -0.78
    yip
    -0.77
    lass
    -0.77
    vernment
    -0.73
     sleeper
    -0.69
    rame
    -0.67
    elaide
    -0.67
    duino
    -0.64
    leans
    -0.63
    POSITIVE LOGITS
    iflower
    1.06
    ified
    0.87
    IFIED
    0.86
    itatively
    0.85
    ifying
    0.84
    ivated
    0.79
    aries
    0.75
    umm
    0.73
    ification
    0.73
    itri
    0.72
    Activations Density 0.086%

    No Known Activations