© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9609
    Prev
    Next
    INDEX
    Explanations

    descriptions of locations near bodies of water, specifically focusing on shorelines

    oai_token-act-pair · gpt-3.5-turbo

    references to shorelines or coastal areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iator
    -0.74
    æł
    -0.74
    ible
    -0.70
     cigarettes
    -0.69
    ombs
    -0.68
    ioch
    -0.67
    ativity
    -0.67
     agon
    -0.65
     fetal
    -0.64
    udes
    -0.64
    POSITIVE LOGITS
    line
    1.24
    lines
    1.15
     shore
    1.00
    side
    0.98
    lands
    0.96
    liner
    0.96
    front
    0.92
    ward
    0.91
    board
    0.88
    yard
    0.88
    Activations Density 0.017%

    No Known Activations