© 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. 10-RES-JB
    6. 16001
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions, beliefs, and wishes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to community input, opinions, and personal beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shades
    -0.64
    abad
    -0.60
     Wonderland
    -0.54
     underest
    -0.53
    vertisement
    -0.52
     <!--
    -0.50
    INTON
    -0.50
    onal
    -0.50
    ATA
    -0.49
    inka
    -0.49
    POSITIVE LOGITS
     of
    1.25
     Of
    0.88
    Of
    0.87
     OF
    0.87
    of
    0.85
     thereof
    0.84
    OF
    0.79
    ims
    0.69
    oft
    0.67
    ij
    0.65
    Activations Density 0.275%

    No Known Activations