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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 22183
    Prev
    Next
    INDEX
    Explanations

    phrases related to heating and lighting

    oai_token-act-pair · gpt-3.5-turbo

    instances of lighting or illumination described in the context of everyday activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Border
    -0.78
    omics
    -0.77
    ocamp
    -0.72
    teness
    -0.71
    grave
    -0.68
    gerald
    -0.68
    ibia
    -0.68
     Spiel
    -0.67
     Border
    -0.67
     Breed
    -0.66
    POSITIVE LOGITS
     heating
    1.49
     electricity
    1.49
     heater
    1.47
     oven
    1.39
     lamps
    1.34
     heat
    1.33
     furnace
    1.33
     cooling
    1.32
     stove
    1.31
     temperature
    1.27
    Activations Density 0.921%

    No Known Activations