© 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. 2-RES-JB
    11. 12617
    Prev
    Next
    INDEX
    Explanations

    specific mentions of proteins or medical substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immunology and specific medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rior
    -0.88
    aday
    -0.86
    bourg
    -0.76
    estones
    -0.74
    rast
    -0.74
    atan
    -0.73
     Sail
    -0.72
    riors
    -0.71
    ese
    -0.71
    sych
    -0.71
    POSITIVE LOGITS
     Beir
    0.92
     Ig
    0.90
     Leban
    0.83
     antibodies
    0.78
     antibody
    0.72
     Lash
    0.69
     sniff
    0.65
     detecting
    0.65
     Glob
    0.64
     è£ıè¦ļéĨĴ
    0.64
    Activations Density 0.025%

    No Known Activations