© 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. 20277
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Finland

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Finland and its attributes

    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
    rooms
    -0.81
    thumbnails
    -0.78
    <<
    -0.74
    het
    -0.66
    imentary
    -0.65
    story
    -0.65
    helle
    -0.65
    gon
    -0.64
    Wheel
    -0.62
    pse
    -0.62
    POSITIVE LOGITS
     Finland
    1.30
     Helsinki
    1.18
     Finnish
    1.05
    ipeg
    0.96
    ä
    0.84
     Paulo
    0.83
    ornia
    0.82
    istani
    0.80
    istan
    0.78
    ö
    0.76
    Activations Density 0.008%

    No Known Activations