© 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. 1-RES-JB
    11. 14455
    Prev
    Next
    INDEX
    Explanations

    references to navigation or direction-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñĭ
    -0.77
    Ñı
    -0.76
    etime
    -0.73
    CLA
    -0.72
    RAW
    -0.72
    chest
    -0.65
    soType
    -0.65
    Closure
    -0.63
    wy
    -0.63
    raq
    -0.63
    POSITIVE LOGITS
     navigation
    1.46
     navig
    1.17
     Navigation
    1.11
     nav
    0.89
     shortcuts
    0.80
     navigate
    0.80
     mathemat
    0.80
     menus
    0.76
    ajo
    0.76
     drawer
    0.75
    Activations Density 0.006%

    No Known Activations