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. 0-RES-JB
    6. 14538
    Prev
    Next
    INDEX
    Explanations

    words related to jewelry and accessories

    oai_token-act-pair · gpt-3.5-turbo

    references to jewelry and related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPA
    -0.83
     Zucker
    -0.78
    elta
    -0.76
     Shuttle
    -0.74
    fn
    -0.71
     Horton
    -0.70
    rans
    -0.69
    iannopoulos
    -0.68
     è£ıç
    -0.67
     coli
    -0.67
    POSITIVE LOGITS
     jewelry
    3.17
     necklace
    2.56
     jew
    2.16
     bracelet
    2.11
     Jewel
    1.91
     jewels
    1.84
    jew
    1.83
    Jew
    1.71
     jewel
    1.69
    ellery
    1.58
    Activations Density 0.052%

    No Known Activations