© 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. 11-RES-JB
    11. 22452
    Prev
    Next
    INDEX
    Explanations

    descriptions or opinions followed by the phrase "the kind of" or "the sort of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that categorize or describe types and classifications of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.62
    foreseen
    -0.58
    çīĪ
    -0.56
    aimon
    -0.54
     simultaneously
    -0.52
     Vulkan
    -0.51
    ocally
    -0.51
    ursday
    -0.50
    ORY
    -0.50
     Nadu
    -0.50
    POSITIVE LOGITS
    liest
    1.10
    est
    1.08
     of
    0.82
    hearted
    0.81
    ling
    0.81
    hest
    0.77
    liness
    0.75
    er
    0.74
    eries
    0.73
    lier
    0.73
    Activations Density 0.029%

    No Known Activations