© 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. 0-RES-JB
    11. 401
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, specifically those with the term "Federation" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to various federations or governing bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haunt
    -0.71
    shell
    -0.71
    tell
    -0.67
    tab
    -0.65
    ounce
    -0.64
    ake
    -0.63
    cook
    -0.63
     mate
    -0.63
     $(
    -0.63
    ose
    -0.61
    POSITIVE LOGITS
     Federation
    4.05
     federation
    2.80
     Confederation
    2.49
    ederation
    2.00
     feder
    1.74
     Association
    1.60
     Union
    1.54
     Confeder
    1.42
     Alliance
    1.40
     Syndicate
    1.37
    Activations Density 0.010%

    No Known Activations