© 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. 8537
    Prev
    Next
    INDEX
    Explanations

    the word "Keep" followed by context or instructions

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases advising the reader to remember or take note of information

    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
    ode
    -0.72
    iliary
    -0.69
    omas
    -0.65
    sonian
    -0.64
    ãģ®æ
    -0.61
    RES
    -0.59
    VICE
    -0.58
    ority
    -0.58
    ilib
    -0.58
    uries
    -0.57
    POSITIVE LOGITS
     tabs
    1.03
     Calm
    0.96
     track
    0.95
     scrolling
    0.92
     kosher
    0.80
     calm
    0.79
     vigil
    0.79
     pace
    0.77
     quiet
    0.75
     humming
    0.75
    Activations Density 0.029%

    No Known Activations