© 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. 7-RES-JB
    11. 11275
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical conditions such as "epilepsy", "seizures", and "thyroid"

    oai_token-act-pair · gpt-3.5-turbo

    topics related to epilepsy and its associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etary
    -0.88
    jamin
    -0.86
    ¯¯
    -0.83
    ciation
    -0.80
    redo
    -0.80
    ered
    -0.79
    cium
    -0.77
    ezvous
    -0.76
    ochet
    -0.76
    elong
    -0.75
    POSITIVE LOGITS
    channelAvailability
    0.64
    ãĥŀ
    0.64
     epilepsy
    0.63
    GY
    0.62
    ulia
    0.61
    ymes
    0.60
     Scroll
    0.60
    960
    0.59
     Beir
    0.59
    onic
    0.59
    Activations Density 0.097%

    No Known Activations