© 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. 18811
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to the term "Tsar."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific family or trademark related to "Ts."

    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
    nesota
    -0.83
    liness
    -0.82
    naissance
    -0.75
    heid
    -0.74
    formance
    -0.73
    drive
    -0.73
    ously
    -0.73
    liest
    -0.71
    cells
    -0.69
    SOURCE
    -0.69
    POSITIVE LOGITS
    izoph
    1.09
     Ts
    1.02
    avorite
    0.94
    arnaev
    0.94
    ouk
    0.87
    arist
    0.86
    rop
    0.84
    annis
    0.84
    achy
    0.80
    etsu
    0.80
    Activations Density 0.007%

    No Known Activations