© 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. 11-RES-JB
    6. 178
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to flying or movement through air

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contraction
    -0.77
    uary
    -0.75
    Footnote
    -0.66
    ricting
    -0.66
     Cumber
    -0.66
     Cros
    -0.65
    otten
    -0.62
    ipation
    -0.61
    _>
    -0.61
    $$$$
    -0.60
    POSITIVE LOGITS
    plane
    0.97
    wheel
    0.93
    trap
    0.91
    planes
    0.90
    past
    0.88
    leaf
    0.86
    whe
    0.83
    paper
    0.83
    weight
    0.83
    bys
    0.83
    Activations Density 0.036%

    No Known Activations