© 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. 2-RES-JB
    6. 18703
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or statements regarding various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "regarding."

    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
    ammy
    -0.77
    orah
    -0.66
    eri
    -0.66
    ierre
    -0.65
    opl
    -0.65
    cart
    -0.65
     Sabha
    -0.65
     Notting
    -0.64
    ©¶æ¥µ
    -0.61
     trap
    -0.60
    POSITIVE LOGITS
     regarding
    0.66
     Regarding
    0.65
    ä¿
    0.65
     cryptocurrencies
    0.64
     legality
    0.63
     respecting
    0.63
     constitu
    0.63
     transactions
    0.63
    ments
    0.63
     RTX
    0.62
    Activations Density 0.042%

    No Known Activations