© 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. 1-RES-JB
    11. 5468
    Prev
    Next
    INDEX
    Explanations

    terms related to interest rates and financial borrowing

    oai_token-act-pair · gpt-3.5-turbo

    references to interest rates in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\
    -0.74
    \\\\\\\\
    -0.69
    女
    -0.68
    abby
    -0.64
    çĦ
    -0.62
    yna
    -0.62
    Plex
    -0.61
     Rudd
    -0.60
    é¾
    -0.60
    ãĤ©
    -0.60
    POSITIVE LOGITS
     interest
    1.11
     Interest
    0.97
    Interest
    0.88
    interest
    0.87
    enza
    0.80
     rates
    0.78
    iculty
    0.77
     Loan
    0.77
     rate
    0.75
     Rates
    0.74
    Activations Density 0.012%

    No Known Activations