© 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. 10-RES-JB
    11. 11244
    Prev
    Next
    INDEX
    Explanations

    words related to the present moment or current events

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing a subject, especially with the word "now."

    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
    natureconservancy
    -0.66
     Institution
    -0.65
     Enhancement
    -0.65
     [|
    -0.62
    æ©
    -0.62
    ked
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
    ulner
    -0.60
    stice
    -0.59
    idad
    -0.58
    POSITIVE LOGITS
    adays
    2.06
    here
    1.59
     imagine
    1.10
     suppose
    1.04
     THAT
    0.89
     Playing
    0.85
    heres
    0.85
     let
    0.84
     lets
    0.84
    herer
    0.83
    Activations Density 0.048%

    No Known Activations