© 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. 10082
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial support, funding, and grants

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial support and funding

    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
    older
    -0.62
    iquette
    -0.59
     Halls
    -0.56
     jaws
    -0.56
    etics
    -0.55
     Ore
    -0.54
    eeks
    -0.54
    estamp
    -0.54
    oya
    -0.53
     specificity
    -0.53
    POSITIVE LOGITS
     by
    1.33
    by
    1.04
     BY
    1.01
     financially
    0.95
    By
    0.92
     partly
    0.91
    bys
    0.90
     through
    0.88
     via
    0.86
     By
    0.84
    Activations Density 0.088%

    No Known Activations