© 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. 10-RES-JB
    11. 11542
    Prev
    Next
    INDEX
    Explanations

    words related to air traffic control and communication

    oai_token-act-pair · gpt-3.5-turbo

    references to air traffic control and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.70
    AppData
    -0.69
    kid
    -0.60
    hement
    -0.59
    apesh
    -0.58
     rhy
    -0.55
    alien
    -0.55
     sho
    -0.55
    abbage
    -0.54
     alphabet
    -0.54
    POSITIVE LOGITS
    govtrack
    0.99
    onica
    0.87
    ologne
    0.73
    kefeller
    0.69
    riers
    0.68
    levision
    0.68
    uably
    0.66
    rollers
    0.66
    ãĥ¼ãĥ³
    0.64
    ridor
    0.64
    Activations Density 0.150%

    No Known Activations