© 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. 1-RES-JB
    11. 14250
    Prev
    Next
    INDEX
    Explanations

    names of political groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    entities related to political factions and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Phys
    -0.71
    Denver
    -0.66
     Wonderland
    -0.65
    Tree
    -0.65
    York
    -0.63
    itialized
    -0.61
     Morph
    -0.60
     Preferred
    -0.59
    Emer
    -0.58
    Hero
    -0.58
    POSITIVE LOGITS
     bloc
    0.86
     dictatorship
    0.86
     communist
    0.82
     nationalist
    0.82
     Cheong
    0.81
     detained
    0.81
     propaganda
    0.80
     separatist
    0.76
     nationalism
    0.75
     UNESCO
    0.75
    Activations Density 2.133%

    No Known Activations