© 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. 0-RES-JB
    11. 8390
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Path" followed by a number, potentially indicating a specific path or direction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to paths or journeys

    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
     blackout
    -0.85
     champagne
    -0.80
     soy
    -0.76
     gag
    -0.75
     punch
    -0.73
     hammer
    -0.73
     espresso
    -0.71
     coffee
    -0.70
     recorder
    -0.70
     popcorn
    -0.68
    POSITIVE LOGITS
     Path
    3.74
    Path
    2.38
    path
    1.78
     PATH
    1.61
     path
    1.29
     paths
    1.27
    PATH
    1.26
     Trails
    1.22
     Perspect
    1.16
     Fate
    1.15
    Activations Density 0.023%

    No Known Activations