© 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. 4-RES-JB
    11. 10679
    Prev
    Next
    INDEX
    Explanations

    terms related to travel itineraries and locations

    oai_token-act-pair · gpt-3.5-turbo

    words associated with itineraries and travel plans

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

    No Comments

    Negative Logits
    tones
    -0.83
    founded
    -0.80
    eries
    -0.79
    fed
    -0.76
    plex
    -0.76
    zynski
    -0.74
    ching
    -0.73
     Intake
    -0.72
    ãĥ£
    -0.71
    bly
    -0.71
    POSITIVE LOGITS
    erers
    0.75
    akings
    0.74
    erer
    0.74
    uary
    0.74
    alam
    0.74
    ogo
    0.73
    adh
    0.72
     itiner
    0.72
    atta
    0.72
    iant
    0.71
    Activations Density 0.034%

    No Known Activations