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. 4-RES-JB
    6. 5323
    Prev
    Next
    INDEX
    Explanations

    instances of the word "well" used in a positive or enhancing context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as well" or similar expressions indicating addition or inclusion

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

    No Comments

    Negative Logits
    anos
    -0.79
    rush
    -0.77
    qua
    -0.70
    anus
    -0.68
    avorite
    -0.68
    iolet
    -0.68
    agara
    -0.67
    mare
    -0.65
    pid
    -0.63
    zan
    -0.63
    POSITIVE LOGITS
    FontSize
    0.71
     liked
    0.68
     behaved
    0.67
     suited
    0.66
     vers
    0.64
    atically
    0.63
    esley
    0.63
    Û
    0.63
    Loading
    0.63
    itect
    0.62
    Activations Density 0.034%

    No Known Activations