© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2515
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    the term "most" in various contexts to indicate importance or prominence

    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
    culosis
    -0.86
    EStream
    -0.83
    ãĥĺãĥ©
    -0.79
    heid
    -0.78
    halla
    -0.77
    é¾įåĸļ士
    -0.75
    phia
    -0.74
    ornia
    -0.74
    ulk
    -0.71
    ãĤ©
    -0.71
    POSITIVE LOGITS
     obvious
    1.39
     salient
    1.28
     important
    1.27
     glaring
    1.26
     noticeable
    1.25
     common
    1.24
     interesting
    1.24
     intriguing
    1.23
     egregious
    1.21
     notable
    1.21
    Activations Density 0.084%

    No Known Activations