© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of transportation and journeys

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "tra" or variations of "traffic" and related terms

    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
     fry
    -0.80
    mint
    -0.79
     ink
    -0.69
     shrinking
    -0.69
     frying
    -0.67
     mint
    -0.66
     calibr
    -0.64
     washing
    -0.63
     congress
    -0.63
     potassium
    -0.63
    POSITIVE LOGITS
    Tra
    3.94
     Tra
    2.27
    tra
    2.21
     TRA
    1.56
     Trail
    1.50
     Traffic
    1.44
     tra
    1.41
     Trails
    1.27
    trak
    1.24
    Tro
    1.20
    Activations Density 0.025%

    No Known Activations