© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 303
    Prev
    Next
    INDEX
    Explanations

    street names or travel routes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific routes or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uster
    -0.86
    iaries
    -0.81
     Hots
    -0.78
    luaj
    -0.78
    endi
    -0.75
    akens
    -0.73
    amily
    -0.71
    ersen
    -0.70
    iary
    -0.69
    ucks
    -0.69
    POSITIVE LOGITS
     routes
    1.09
     route
    1.02
    route
    0.97
    Route
    0.95
     Route
    0.84
    WAY
    0.81
    nels
    0.80
    finding
    0.79
    WAYS
    0.75
     routing
    0.75
    Activations Density 0.023%

    No Known Activations