© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    6. 12133
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare, health insurance, and medical system policies

    oai_token-act-pair · gpt-3.5-turbo

    references to single-payer healthcare systems and their opposition

    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
    ouri
    -0.64
     Scand
    -0.63
     Highlands
    -0.61
     Crus
    -0.61
     Monsters
    -0.61
     Jonah
    -0.60
    oub
    -0.59
     Devils
    -0.58
     Jeep
    -0.58
    dar
    -0.58
    POSITIVE LOGITS
    payer
    1.20
    yright
    1.01
    oples
    0.91
    backer
    0.88
    riors
    0.83
    ledged
    0.81
    ysis
    0.79
    anced
    0.78
    payers
    0.76
    ternity
    0.74
    Activations Density 0.009%

    No Known Activations