© 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. 1-RES-JB
    11. 14510
    Prev
    Next
    INDEX
    Explanations

    mentions of insurance

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to insurance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urb
    -0.77
    hunt
    -0.76
    leon
    -0.73
     Atmosp
    -0.72
    inant
    -0.71
    ebook
    -0.71
    Pad
    -0.70
    adj
    -0.69
    cold
    -0.69
    reet
    -0.68
    POSITIVE LOGITS
     insurance
    1.35
     premiums
    1.25
     Insurance
    1.12
     insurer
    1.11
     issuer
    1.10
     insurers
    1.10
     broker
    1.03
     provider
    0.99
     brokerage
    0.97
    urance
    0.95
    Activations Density 0.020%

    No Known Activations