© 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. 11-RES-JB
    11. 7782
    Prev
    Next
    INDEX
    Explanations

    information related to financial holdings, investments, and economic sectors

    oai_token-act-pair · gpt-3.5-turbo

    financial and economic indicators or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igent
    -0.63
    ĸļ
    -0.57
    ãĥ¯ãĥ³
    -0.53
    ppy
    -0.52
     authent
    -0.52
    Ĥ¬
    -0.51
    venth
    -0.51
    WARNING
    -0.50
    nant
    -0.50
    von
    -0.49
    POSITIVE LOGITS
     GDP
    1.07
     GST
    1.06
     dividend
    1.04
     depreciation
    1.02
     Debt
    1.02
     liquidity
    0.98
     inflation
    0.98
     dividends
    0.95
     debt
    0.94
     revenues
    0.93
    Activations Density 0.659%

    No Known Activations