Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 145
    Prev
    Next
    INDEX
    Explanations

    the word "beyond"

    oai_token-act-pair · gpt-4-turbo

    phrases indicating going or extending beyond a certain point or limit

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of exceeding limits or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assass
    -0.83
    è¦ļéĨĴ
    -0.72
    yah
    -0.71
    ARS
    -0.70
    lee
    -0.66
    chem
    -0.66
    baugh
    -0.64
     Mehran
    -0.64
    cu
    -0.63
    Mu
    -0.63
    POSITIVE LOGITS
    ĸļ
    0.79
     beyond
    0.76
     comprehension
    0.76
    astical
    0.72
     imagining
    0.71
    esis
    0.71
    =>
    0.71
     Horizons
    0.70
     Greece
    0.70
    lehem
    0.69
    Activations Density 0.014%

    No Known Activations