© 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. 2-RES-JB
    11. 12734
    Prev
    Next
    INDEX
    Explanations

    instances where funding is mentioned or discussed in the context of various projects or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "funded" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alter
    -0.76
    ijn
    -0.73
    vent
    -0.72
    css
    -0.72
     Spice
    -0.71
    Son
    -0.70
    士
    -0.68
    lime
    -0.66
    apple
    -0.66
    uber
    -0.64
    POSITIVE LOGITS
     funded
    1.10
     financed
    1.01
    funded
    0.98
     funding
    0.93
    nesday
    0.88
    amental
    0.79
     budgets
    0.77
     fundra
    0.76
    paren
    0.76
     scholarships
    0.75
    Activations Density 0.017%

    No Known Activations