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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10659
    Prev
    Next
    INDEX
    Explanations

    the word "tra" followed by other letters, possibly "iler", and "ffic"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to traffic and transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.91
    lihood
    -0.69
    lain
    -0.69
     Seym
    -0.64
    amental
    -0.63
     Mortal
    -0.63
    CLUD
    -0.62
     proportional
    -0.62
     unconditional
    -0.61
    arian
    -0.59
    POSITIVE LOGITS
    quel
    0.99
    itored
    0.90
    ffic
    0.89
    pped
    0.84
    verse
    0.83
    ordinary
    0.82
    pping
    0.78
    umat
    0.77
    pling
    0.77
    Tra
    0.77
    Activations Density 0.008%

    No Known Activations