© 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
    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. 937
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "warranty"

    oai_token-act-pair · gpt-4-turbo

    phrases related to warranties

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to warranty and product guarantees

    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
    apo
    -0.88
    romeda
    -0.81
    erva
    -0.80
    omsky
    -0.80
    apest
    -0.79
    eto
    -0.76
    arters
    -0.76
    ellen
    -0.76
    esta
    -0.74
    sen
    -0.72
    POSITIVE LOGITS
     warranty
    1.15
     warranties
    1.07
     Warranty
    0.94
    BuyableInstoreAndOnline
    0.76
     UL
    0.75
     WARRANT
    0.75
     repair
    0.73
     exclus
    0.71
     reliability
    0.70
     complimentary
    0.68
    Activations Density 0.024%

    No Known Activations