Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19230
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds and reactions, specifically focusing on hydrogen and propellants

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbo
    -0.74
     Languages
    -0.72
     CLSID
    -0.69
    onym
    -0.67
    meaning
    -0.66
     Nieto
    -0.65
    ä¹
    -0.62
    aird
    -0.62
     Leilan
    -0.61
     Own
    -0.61
    POSITIVE LOGITS
     chloride
    0.97
     gases
    0.89
     beverages
    0.87
     heater
    0.84
     beverage
    0.84
     capacitor
    0.83
     electroly
    0.82
     cooled
    0.82
    ylene
    0.81
     piping
    0.81
    Activations Density 0.119%

    No Known Activations