© 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. 4-RES-JB
    11. 22074
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically focusing on events that happened long ago

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, specifically referencing "long ago" or "not long after."

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

    No Comments

    Negative Logits
    pert
    -0.77
     Avatar
    -0.68
    gencies
    -0.67
    alam
    -0.65
    initely
    -0.65
    mund
    -0.64
    gem
    -0.63
    origin
    -0.63
    yna
    -0.62
    usalem
    -0.61
    POSITIVE LOGITS
     obser
    0.76
     nor
    0.75
     Colleges
    0.73
    NetMessage
    0.71
     anymore
    0.70
    acement
    0.65
    ãĥ¼ãĥ³
    0.64
     Enough
    0.64
    \/\/
    0.63
     parting
    0.60
    Activations Density 0.049%

    No Known Activations