© 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. 11-RES-JB
    11. 3485
    Prev
    Next
    INDEX
    Explanations

    information related to financial reports and findings

    oai_token-act-pair · gpt-3.5-turbo

    references to reports and analyses related to taxation and economic assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -0.97
     Whilst
    -0.94
     secondly
    -0.83
     recognise
    -0.83
     CCTV
    -0.81
    Firstly
    -0.80
     util
    -0.78
     paed
    -0.78
     apologise
    -0.77
     rumours
    -0.77
    POSITIVE LOGITS
     nonpartisan
    1.22
     economists
    1.09
     Brookings
    1.06
     Legislative
    1.06
     economist
    1.03
     lobbyist
    1.02
     POLITICO
    1.00
     Kaiser
    1.00
     Cato
    1.00
     actu
    0.98
    Activations Density 0.508%

    No Known Activations