© 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. 2-RES-JB
    11. 17254
    Prev
    Next
    INDEX
    Explanations

    terms related to jet engines or aircraft

    oai_token-act-pair · gpt-3.5-turbo

    references to jets or jet-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.72
    UGC
    -0.72
    éģ
    -0.72
    Honest
    -0.68
    Constructed
    -0.68
    PUT
    -0.66
    «ĺ
    -0.66
    ãĤ±
    -0.65
    ettings
    -0.65
     NRS
    -0.64
    POSITIVE LOGITS
    liner
    1.41
    liners
    1.19
     jet
    1.14
     jets
    1.13
     airliner
    1.05
    plane
    0.95
     planes
    0.95
     airplanes
    0.92
     plane
    0.91
    planes
    0.91
    Activations Density 0.007%

    No Known Activations