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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 17140
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement and travel

    oai_token-act-pair · gpt-3.5-turbo

    the concept of navigating through various contexts or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lor
    -0.65
     Brent
    -0.64
     grain
    -0.63
     Cry
    -0.62
    stri
    -0.62
     Lump
    -0.62
    Intel
    -0.62
     CIS
    -0.61
     Lust
    -0.60
     Rib
    -0.60
    POSITIVE LOGITS
     navigate
    3.56
     navigating
    2.70
     navig
    2.28
     navigation
    1.63
    Nav
    1.38
     traverse
    1.34
     Navigation
    1.26
    nav
    1.22
     browse
    1.17
     Nav
    1.13
    Activations Density 0.010%

    No Known Activations