© 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. 0-RES-JB
    11. 11809
    Prev
    Next
    INDEX
    Explanations

    dates or forms of expression related to time and frequency

    oai_token-act-pair · gpt-3.5-turbo

    words ending in the suffix "ly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bag
    -0.66
     induced
    -0.65
     epid
    -0.64
     Piet
    -0.62
     belonging
    -0.59
    rest
    -0.58
     mapping
    -0.58
     Nav
    -0.58
     promotion
    -0.58
     implementing
    -0.58
    POSITIVE LOGITS
    LY
    4.39
    ALLY
    1.71
    LI
    1.71
    ELY
    1.71
    ILY
    1.54
    LINE
    1.54
    ly
    1.53
    NESS
    1.46
    LIN
    1.34
    LO
    1.30
    Activations Density 0.016%

    No Known Activations