© 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. 18092
    Prev
    Next
    INDEX
    Explanations

    words related to aircraft and aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to aircraft

    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
     Wit
    -0.79
    roots
    -0.78
    zn
    -0.77
    ealous
    -0.76
    kins
    -0.74
    galitarian
    -0.71
     Fiona
    -0.66
    liter
    -0.65
    Stone
    -0.65
     Stranger
    -0.64
    POSITIVE LOGITS
     aircraft
    3.42
     Aircraft
    2.73
     airplanes
    2.40
     airplane
    2.30
     planes
    2.30
    ircraft
    2.22
     aviation
    2.14
     airliner
    1.99
     plane
    1.97
     jets
    1.91
    Activations Density 0.012%

    No Known Activations