© 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. 4-RES-JB
    11. 709
    Prev
    Next
    INDEX
    Explanations

    phrases related to the historical entity "Continental Congress."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'Continental' as it relates to various contexts, including historical and geographical themes

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

    No Comments

    Negative Logits
    Downloadha
    -0.91
    rained
    -0.90
    edin
    -0.87
    rooms
    -0.85
    isSpecialOrderable
    -0.84
    Reply
    -0.83
    anamo
    -0.81
    allah
    -0.78
    bsp
    -0.78
    epad
    -0.78
    POSITIVE LOGITS
     continental
    1.12
     Continental
    1.07
     drift
    0.88
     superiority
    0.82
    continental
    0.81
     crust
    0.80
     Divide
    0.80
     shelf
    0.80
     congress
    0.79
     STATES
    0.79
    Activations Density 0.007%

    No Known Activations