© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal or medical contexts, particularly words ending in 'ase'

    oai_token-act-pair · gpt-3.5-turbo

    the term "ase" in various contexts, likely relating to enzymes or medical conditions

    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
    ¥ŀ
    -0.85
    è¦ļéĨĴ
    -0.79
    lished
    -0.71
    ersive
    -0.70
     tremend
    -0.65
    ãĤ©
    -0.64
    enegger
    -0.63
    antle
    -0.63
    rities
    -0.63
    catentry
    -0.62
    POSITIVE LOGITS
    xual
    1.51
    ase
    1.03
    asing
    0.85
    lease
    0.82
    lly
    0.80
    ases
    0.79
    construct
    0.76
     inhibitors
    0.72
    pee
    0.71
    ably
    0.71
    Activations Density 0.011%

    No Known Activations