Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20967
    Prev
    Next
    INDEX
    Explanations

    references to insurance-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to insurance and related terms

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

    No Comments

    Negative Logits
    anism
    -0.86
    urb
    -0.83
    leon
    -0.82
    lihood
    -0.79
    hunt
    -0.78
    lins
    -0.77
    ebook
    -0.77
    inant
    -0.76
    tle
    -0.75
    quart
    -0.74
    POSITIVE LOGITS
     premiums
    1.25
     insurance
    1.15
     broker
    1.06
     issuer
    1.04
     insurers
    0.97
     insurer
    0.95
     provider
    0.94
     Insurance
    0.94
     carriers
    0.94
     brokerage
    0.93
    Activations Density 0.022%

    No Known Activations