Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4520
    Prev
    Next
    INDEX
    Explanations

    phrases related to going on trips or visits

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical journeys or travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iola
    -0.88
    Tracker
    -0.69
    fortunately
    -0.68
    phia
    -0.66
    ellar
    -0.65
    affer
    -0.64
    voice
    -0.63
    sis
    -0.63
    SOURCE
    -0.63
    breaks
    -0.63
    POSITIVE LOGITS
     Wonderland
    0.96
     Ivy
    0.75
    odan
    0.68
     Tour
    0.67
     Mecca
    0.66
     Nationals
    0.66
     Mer
    0.64
     Somerset
    0.64
     TOUR
    0.61
     appease
    0.61
    Activations Density 0.352%

    No Known Activations