© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2343
    Prev
    Next
    INDEX
    Explanations

    terms related to specific geological time periods, in particular the Paleocene and Eocene epochs

    oai_token-act-pair · gpt-3.5-turbo

    references to geological epochs and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¦
    -0.87
    puff
    -0.80
    NESS
    -0.77
    partial
    -0.72
    æĦ
    -0.71
    INA
    -0.71
    å¦
    -0.69
    NEY
    -0.69
    Letter
    -0.69
    wagon
    -0.68
    POSITIVE LOGITS
    ocene
    1.68
    olithic
    1.43
     Warfare
    1.14
    ozo
    1.03
    osaurs
    1.00
    vironment
    0.95
     prehistoric
    0.91
    azo
    0.91
     epoch
    0.90
     civilisation
    0.89
    Activations Density 0.024%

    No Known Activations