© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17545
    Prev
    Next
    INDEX
    Explanations

    phrases related to liquefied natural gas (LNG)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to liquefied natural gas and references to coffee

    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
     Panther
    -0.79
    ãĥ£
    -0.75
    rior
    -0.74
    riors
    -0.74
     Resolution
    -0.72
     headache
    -0.70
     grou
    -0.66
     headaches
    -0.66
     Malays
    -0.66
    ned
    -0.66
    POSITIVE LOGITS
    inders
    0.89
    elines
    0.87
    cript
    0.87
    epad
    0.84
    inson
    0.83
    ĸļ
    0.81
    ancies
    0.79
    isse
    0.78
    say
    0.78
    estyles
    0.77
    Activations Density 0.030%

    No Known Activations