© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    terms related to geothermal energy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geothermal energy and dynamics

    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
     tears
    -0.70
     pas
    -0.67
     retire
    -0.67
     spr
    -0.64
    à¸
    -0.64
     tags
    -0.63
     mang
    -0.63
     Churchill
    -0.62
    eat
    -0.61
     cheers
    -0.61
    POSITIVE LOGITS
    othermal
    4.02
    odynamic
    1.82
    odynamics
    1.47
    odynam
    1.31
     tidal
    1.15
    forge
    1.02
    ansom
    1.02
    ataka
    0.98
    rical
    0.97
    otherapy
    0.94
    Activations Density 0.038%

    No Known Activations