© 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. 8-RES-JB
    11. 17826
    Prev
    Next
    INDEX
    Explanations

    terms related to fundraising, rewards, and pledges

    oai_token-act-pair · gpt-3.5-turbo

    fundraising and financial support activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.90
    baugh
    -0.77
    irit
    -0.72
    uv
    -0.71
    otropic
    -0.66
     grounding
    -0.65
     turbulence
    -0.64
    erguson
    -0.64
     esp
    -0.63
     resil
    -0.63
    POSITIVE LOGITS
     bidder
    1.22
     donations
    1.14
     submissions
    1.13
     prize
    1.10
     Prize
    1.10
     prizes
    1.10
     PayPal
    1.08
     Kickstarter
    1.07
     entrants
    1.06
     Participant
    1.05
    Activations Density 1.031%

    No Known Activations