© 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. 2848
    Prev
    Next
    INDEX
    Explanations

    mentions of various countries and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and their political or military involvement

    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
    Els
    -0.64
     eternity
    -0.62
    ãĥł
    -0.61
    tnc
    -0.60
    ixt
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    âĶĢâĶĢâĶĢâĶĢ
    -0.58
    Translation
    -0.58
    ãĥĥãĥī
    -0.57
    Zip
    -0.57
    POSITIVE LOGITS
     denies
    1.25
     accuses
    1.22
     meanwhile
    1.18
     reacted
    1.16
     insists
    1.14
     spokesman
    1.13
     contends
    1.12
     responded
    1.12
     opposes
    1.09
     appealed
    1.07
    Activations Density 0.340%

    No Known Activations