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. 6-RES-JB
    6. 19504
    Prev
    Next
    INDEX
    Explanations

    phrases related to maximizing quantity or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of maximizing or increasing potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.97
    riad
    -0.82
    wa
    -0.72
    heavy
    -0.67
    rollers
    -0.67
    yard
    -0.67
    roller
    -0.67
     Vish
    -0.65
    ware
    -0.65
    rique
    -0.65
    POSITIVE LOGITS
     dstg
    0.96
     sidx
    0.73
     srfAttach
    0.73
    ãĥīãĥ©ãĤ´ãĥ³
    0.70
     introdu
    0.67
    TPPStreamerBot
    0.67
     indication
    0.64
    iary
    0.64
     distingu
    0.63
    Versions
    0.63
    Activations Density 0.020%

    No Known Activations