© 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. 7-RES-JB
    11. 1431
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and offering condolences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of condolences and sympathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.64
    é¾
    -0.61
    itamin
    -0.61
     Surve
    -0.61
     tended
    -0.60
     toilets
    -0.59
     famously
    -0.59
     disliked
    -0.58
     trailed
    -0.57
     Canal
    -0.55
    POSITIVE LOGITS
     unres
    1.01
     condolences
    0.98
     sincerely
    0.91
    ========
    0.83
    bly
    0.81
     congratulate
    0.81
     respects
    0.76
     grateful
    0.74
     sincere
    0.73
     thankful
    0.73
    Activations Density 0.240%

    No Known Activations