© 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. 10208
    Prev
    Next
    INDEX
    Explanations

    countries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnic 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
    rex
    -0.97
    apego
    -0.93
    ifice
    -0.92
    utics
    -0.84
    illance
    -0.84
    ologies
    -0.83
    utherford
    -0.81
    ivism
    -0.81
    anship
    -0.76
    pter
    -0.76
    POSITIVE LOGITS
    istani
    0.97
     Portuguese
    0.88
     citiz
    0.88
     Nadu
    0.85
     nationals
    0.77
     entertain
    0.77
     civil
    0.75
     immigrant
    0.75
     embassies
    0.74
     intellig
    0.73
    Activations Density 0.035%

    No Known Activations