© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    financial transactions and funding sources

    oai_token-act-pair · gpt-3.5-turbo

    sources of funding and financial contributions

    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
    icter
    -0.77
    onder
    -0.74
    isky
    -0.74
    zu
    -0.73
    onential
    -0.72
    perfect
    -0.72
    faced
    -0.71
    ctrl
    -0.70
    spect
    -0.70
    Í
    -0.70
    POSITIVE LOGITS
     taxpayers
    1.51
     donations
    1.34
     taxpayer
    1.34
     taxes
    1.25
     royalties
    1.23
     donors
    1.22
     fees
    1.20
     taxation
    1.13
     treasury
    1.12
     coffers
    1.09
    Activations Density 0.201%

    No Known Activations