© 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. 8-RES-JB
    11. 1276
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the Netherlands

    oai_token-act-pair · gpt-3.5-turbo

    references to the Dutch or Netherlands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vae
    -0.79
    ctic
    -0.71
    icago
    -0.71
    azine
    -0.71
    natureconservancy
    -0.70
    zona
    -0.68
    ovie
    -0.68
    ctica
    -0.66
    utterstock
    -0.66
    abilia
    -0.66
    POSITIVE LOGITS
    lander
    0.86
    ijk
    0.85
     Netherlands
    0.85
    men
    0.83
    man
    0.82
    mans
    0.81
    geist
    0.77
    chal
    0.77
    sterdam
    0.77
     Indies
    0.77
    Activations Density 0.045%

    No Known Activations