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. 8-RES-JB
    6. 4711
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "stand by" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of "standing by" or providing support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilib
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
     resonance
    -0.70
    igon
    -0.67
    Lear
    -0.65
    owler
    -0.65
    cin
    -0.65
    requisite
    -0.64
     proble
    -0.64
    elf
    -0.63
    POSITIVE LOGITS
     sidelines
    0.90
     steadfast
    0.89
     Defenders
    0.76
     vigil
    0.73
     indef
    0.68
     uncond
    0.68
    amental
    0.66
     defenders
    0.66
     denying
    0.64
    edly
    0.64
    Activations Density 0.086%

    No Known Activations