© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11434
    Prev
    Next
    INDEX
    Explanations

    information related to funding sources and grants in research

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing funding sources and financial support for research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brut
    -0.75
    terness
    -0.74
    apes
    -0.72
    ettings
    -0.70
     havoc
    -0.69
     lifeless
    -0.69
    paio
    -0.68
    isson
    -0.68
     inacc
    -0.68
    scape
    -0.67
    POSITIVE LOGITS
     grants
    1.39
     concess
    1.35
     donations
    1.35
     grant
    1.29
     funding
    1.26
     donation
    1.23
     funds
    1.22
     philanthrop
    1.22
     Funding
    1.20
     donors
    1.17
    Activations Density 0.378%

    No Known Activations