© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5446
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions or treatments, especially those ending in 'ith'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isco
    -0.71
    ktop
    -0.69
    PDATE
    -0.66
    eca
    -0.65
     jams
    -0.60
    cks
    -0.59
     Licensed
    -0.59
     mileage
    -0.58
    ptions
    -0.57
    encies
    -0.57
    POSITIVE LOGITS
    uania
    1.18
    iasis
    1.13
    yll
    1.06
    romy
    1.03
    iop
    0.99
    gow
    0.97
    urst
    0.93
    otle
    0.93
    ttp
    0.90
    reading
    0.89
    Activations Density 0.048%

    No Known Activations