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. 1-RES-JB
    6. 1187
    Prev
    Next
    INDEX
    Explanations

    words related to valuable items, specifically jewels and ornaments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with precious items and decorations, particularly relating to jewels and ornaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irrel
    -0.67
     Rough
    -0.65
    due
    -0.64
    olves
    -0.63
    ACTION
    -0.62
    android
    -0.62
    natural
    -0.61
     intermittent
    -0.61
    andan
    -0.60
    verbal
    -0.60
    POSITIVE LOGITS
     jewels
    1.35
     jewel
    1.24
    engers
    0.87
     Jewel
    0.83
     thief
    0.83
    gow
    0.80
    stones
    0.79
    ograph
    0.78
     ornament
    0.78
    nuts
    0.77
    Activations Density 0.007%

    No Known Activations