© 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. 0-RES-JB
    11. 11710
    Prev
    Next
    INDEX
    Explanations

    terms related to mortgages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "mortgage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĸº
    -0.72
    prot
    -0.71
    âĪ
    -0.69
     Vel
    -0.68
     Xuan
    -0.67
     Steph
    -0.65
     Tant
    -0.64
    Æ
    -0.63
     Ach
    -0.63
    bek
    -0.63
    POSITIVE LOGITS
     mortgage
    3.50
     mortgages
    2.86
     Mortgage
    2.65
     foreclosure
    2.05
     mortg
    1.93
    gage
    1.75
     lender
    1.71
     loan
    1.59
     lenders
    1.58
     loans
    1.52
    Activations Density 0.019%

    No Known Activations