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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5897
    Prev
    Next
    INDEX
    Explanations

    phrases related to insurance and liability coverage

    oai_token-act-pair · gpt-3.5-turbo

    issues related to corporate insurance and liability challenges

    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
    ilib
    -0.84
     Wad
    -0.83
    airo
    -0.81
    Gamer
    -0.79
     Dag
    -0.75
    RAW
    -0.74
    Clock
    -0.72
    sworth
    -0.72
    Ec
    -0.71
    rogram
    -0.70
    POSITIVE LOGITS
     insurer
    2.16
     insurance
    2.11
     insured
    2.04
     insurers
    2.04
     Insurance
    1.92
    insured
    1.88
     premiums
    1.85
     deductible
    1.65
     insure
    1.63
     uninsured
    1.60
    Activations Density 0.300%

    No Known Activations