© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 7656
    Prev
    Next
    INDEX
    Explanations

    phrases related to following a specific course or direction, especially in a metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of paths

    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
     Royale
    -0.66
    ibur
    -0.66
    atches
    -0.65
     weddings
    -0.65
     Aires
    -0.65
    iots
    -0.64
    tons
    -0.63
    ishers
    -0.63
    Commercial
    -0.63
    hips
    -0.63
    POSITIVE LOGITS
     path
    3.79
     paths
    2.86
    path
    2.54
     Path
    2.40
     pathway
    2.19
    Path
    2.03
     PATH
    1.86
     trajectory
    1.70
    PATH
    1.61
     pathways
    1.60
    Activations Density 0.033%

    No Known Activations