© 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. 16686
    Prev
    Next
    INDEX
    Explanations

    references to countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to "nation" or concepts related to national identity

    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
    SCP
    -0.66
    HB
    -0.65
    wd
    -0.64
     Extension
    -0.63
    abilities
    -0.60
    achi
    -0.59
    achy
    -0.59
    CLA
    -0.58
     Alison
    -0.58
    aurus
    -0.58
    POSITIVE LOGITS
     nation
    3.51
     country
    2.38
     nations
    2.04
     Nation
    2.03
    nation
    1.85
    Nation
    1.75
     national
    1.58
     continent
    1.49
    country
    1.43
     Country
    1.35
    Activations Density 0.015%

    No Known Activations