© 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 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. 4346
    Prev
    Next
    INDEX
    Explanations

    words related to government policies and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    discussions around urban policy and social equity issues

    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
    DragonMagazine
    -0.86
    Legend
    -0.80
    yssey
    -0.78
    wang
    -0.69
     Riy
    -0.69
    eared
    -0.69
     Alexand
    -0.67
    Fans
    -0.67
    é¾įåĸļ士
    -0.66
     Telegram
    -0.66
    POSITIVE LOGITS
     legislatures
    1.32
     prohibitions
    1.28
     punitive
    1.22
     incentives
    1.21
     societal
    1.20
     taxation
    1.20
     governmental
    1.19
     curric
    1.18
     policies
    1.17
     coercive
    1.17
    Activations Density 0.580%

    No Known Activations