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. 0-RES-JB
    6. 10777
    Prev
    Next
    INDEX
    Explanations

    references related to gas, specifically natural gas

    oai_token-act-pair · gpt-3.5-turbo

    references to gas and natural gas

    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
     jud
    -0.66
     Presbyterian
    -0.64
     Subject
    -0.63
     Chairman
    -0.61
     rook
    -0.60
     Chancellor
    -0.59
     pivot
    -0.59
     chairman
    -0.59
     rendered
    -0.58
     Cardinal
    -0.58
    POSITIVE LOGITS
    gas
    5.03
    Gas
    2.06
     gas
    1.68
    ga
    1.63
     Gas
    1.53
    gel
    1.23
    gem
    1.20
    gart
    1.18
     gases
    1.15
    gs
    1.14
    Activations Density 0.016%

    No Known Activations