© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9200
    Prev
    Next
    INDEX
    Explanations

    words related to liquefied natural gas (LNG)

    oai_token-act-pair · gpt-3.5-turbo

    references to liquefied natural gas and related terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rior
    -0.88
    verty
    -0.77
     Neph
    -0.66
     Panda
    -0.66
     Indians
    -0.65
     Panther
    -0.65
     sar
    -0.64
     Hiroshima
    -0.64
     flap
    -0.63
     Bengal
    -0.62
    POSITIVE LOGITS
     liqu
    1.17
    ĸļ
    0.98
     Liqu
    0.96
    orem
    0.95
    ipedia
    0.93
    essee
    0.91
    ovie
    0.87
    antine
    0.86
    orable
    0.86
    etooth
    0.84
    Activations Density 0.014%

    No Known Activations