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. 14993
    Prev
    Next
    INDEX
    Explanations

    words related to jewelry items like bracelets, necklaces, and amulets

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of jewelry and magical items

    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
    apeake
    -0.78
     srf
    -0.75
    driving
    -0.68
    eatures
    -0.65
    DEM
    -0.65
     neighb
    -0.65
    blogs
    -0.62
    arro
    -0.62
     environments
    -0.61
    iasco
    -0.61
    POSITIVE LOGITS
     necklace
    0.89
     amulet
    0.85
     bracelet
    0.84
    worm
    0.79
    wra
    0.78
     holder
    0.78
    binding
    0.74
    worms
    0.73
    head
    0.73
     inscribed
    0.73
    Activations Density 0.045%

    No Known Activations