© 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 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. 14906
    Prev
    Next
    INDEX
    Explanations

    scientific journal names, specifically "Nature"

    oai_token-act-pair · gpt-3.5-turbo

    references to the journal "Nature."

    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
    ardless
    -0.84
    acters
    -0.84
    rons
    -0.84
    rican
    -0.76
    aged
    -0.75
    oning
    -0.72
    ages
    -0.71
    minster
    -0.70
    kers
    -0.70
    olded
    -0.70
    POSITIVE LOGITS
     Nature
    1.02
    nature
    0.88
    Nature
    0.83
     Conservation
    0.83
     Pwr
    0.79
     Conserv
    0.74
     Neuroscience
    0.70
    uality
    0.70
    Tree
    0.70
     Genetics
    0.69
    Activations Density 0.007%

    No Known Activations