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. 4-RES-JB
    6. 17687
    Prev
    Next
    INDEX
    Explanations

    descriptions of energy production methods

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to energy production and environmental sustainability

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

    No Comments

    Negative Logits
    answered
    -0.77
     inconsistency
    -0.71
     circumstance
    -0.71
     adversity
    -0.70
     spoiler
    -0.67
     Gamer
    -0.67
    zzy
    -0.66
     Sorceress
    -0.66
     coward
    -0.66
     poems
    -0.66
    POSITIVE LOGITS
     warehouses
    0.92
     subsidiaries
    0.92
     tariffs
    0.90
     leased
    0.89
     tariff
    0.89
     wastewater
    0.87
     headquartered
    0.87
     subcontract
    0.86
     revenue
    0.85
     cheaper
    0.85
    Activations Density 1.625%

    No Known Activations