© 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. 11438
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding and financing various activities or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    funding-related terms, particularly those associated with governmental or organizational budgets and financial commitments

    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
    ĸļ
    -0.92
    verb
    -0.75
     twist
    -0.74
    onyms
    -0.74
    heard
    -0.74
    iquette
    -0.73
    xual
    -0.69
     Unsure
    -0.68
    1001
    -0.66
    notations
    -0.65
    POSITIVE LOGITS
     upkeep
    1.23
     coffers
    1.11
     salaries
    1.05
     projects
    1.03
     expenditure
    1.03
     expenses
    1.01
     infrastructure
    1.00
     expenditures
    1.00
     treasury
    0.98
     reconstruction
    0.96
    Activations Density 0.454%

    No Known Activations