© 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. 10-RES-JB
    11. 10187
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters, specifically tax-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to tax returns and related financial disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zai
    -0.77
    prot
    -0.76
    aptic
    -0.72
     calming
    -0.70
    Kill
    -0.70
     Reaction
    -0.69
     bystand
    -0.69
    lethal
    -0.69
     utopian
    -0.68
     Enlight
    -0.67
    POSITIVE LOGITS
     filings
    1.55
     IRS
    1.47
     audits
    1.46
     taxable
    1.43
     audit
    1.38
     accountant
    1.38
     FEC
    1.37
     receipts
    1.31
     disclosures
    1.30
     Revenue
    1.27
    Activations Density 0.608%

    No Known Activations