© 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. 0-RES-JB
    6. 14823
    Prev
    Next
    INDEX
    Explanations

    phrases related to aerial activities or aircraft

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of flying

    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
    ournals
    -0.76
    pedia
    -0.72
    tion
    -0.71
    tsky
    -0.71
    asc
    -0.70
    eworks
    -0.69
    olitan
    -0.68
     Medicaid
    -0.68
    itcher
    -0.67
    ovember
    -0.67
    POSITIVE LOGITS
     flying
    3.61
    flying
    2.50
     Flying
    2.25
    Flying
    2.20
     fly
    2.03
     flown
    1.98
     flies
    1.96
     flew
    1.92
     sailing
    1.80
     flight
    1.66
    Activations Density 0.023%

    No Known Activations