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. 10-RES-JB
    6. 18060
    Prev
    Next
    INDEX
    Explanations

    words related to optimization and minimizing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to optimization and minimization strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holder
    -0.67
     dove
    -0.61
    hold
    -0.61
     Kimber
    -0.61
     principal
    -0.61
    NetMessage
    -0.60
     faithfully
    -0.59
     boldly
    -0.58
     chalk
    -0.58
     shed
    -0.57
    POSITIVE LOGITS
    ising
    1.56
    isation
    1.48
    ise
    1.43
    izes
    1.43
    ised
    1.41
    ally
    1.40
    isations
    1.39
    ization
    1.32
    ises
    1.31
    izations
    1.29
    Activations Density 0.055%

    No Known Activations