© 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. 11-RES-JB
    11. 20393
    Prev
    Next
    INDEX
    Explanations

    mentions of government policies, regulations, and international relations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to regulatory and governmental issues

    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
     freaking
    -0.80
     cops
    -0.79
     buddies
    -0.76
     phony
    -0.76
     colorful
    -0.75
    JUST
    -0.75
     dudes
    -0.75
     afterward
    -0.73
     Nope
    -0.73
     .)
    -0.73
    POSITIVE LOGITS
     organis
    1.26
     recognised
    1.25
     Whilst
    1.25
     emphas
    1.21
     envis
    1.21
     recognise
    1.18
     util
    1.16
     ageing
    1.12
     adversely
    1.12
     favourable
    1.10
    Activations Density 0.962%

    No Known Activations