© 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. 11-RES-JB
    11. 7662
    Prev
    Next
    INDEX
    Explanations

    words related to implications and applications of scientific research

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical research and its implications for health treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ontent
    -0.80
    rals
    -0.76
    adelphia
    -0.69
    lishes
    -0.68
    Lago
    -0.67
    portion
    -0.67
     Pound
    -0.66
    76561
    -0.65
    erate
    -0.64
    trak
    -0.64
    POSITIVE LOGITS
     neuroscience
    1.38
     therape
    1.38
     biomedical
    1.36
     therapies
    1.33
     biom
    1.25
     biology
    1.24
     diseases
    1.18
     medicine
    1.17
     molecular
    1.16
     understanding
    1.14
    Activations Density 0.363%

    No Known Activations