© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13117
    Prev
    Next
    INDEX
    Explanations

    words related to travel destinations

    oai_token-act-pair · gpt-3.5-turbo

    words related to travel locations or destinations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    appa
    -0.85
    ulate
    -0.81
    ucket
    -0.79
    aps
    -0.75
    ooks
    -0.74
    tymology
    -0.72
    igan
    -0.72
    inventoryQuantity
    -0.71
    ophon
    -0.70
    abi
    -0.70
    POSITIVE LOGITS
     destination
    1.01
     Destination
    1.01
     whence
    0.87
     destinations
    0.87
     traveler
    0.74
     Lisbon
    0.72
     location
    0.68
     Cruise
    0.67
     TBA
    0.65
     Mecca
    0.64
    Activations Density 0.022%

    No Known Activations