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. 20894
    Prev
    Next
    INDEX
    Explanations

    mentions of precious stones, particularly diamonds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of diamonds and other precious stones

    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
     McA
    -0.94
    SPONSORED
    -0.81
     Andersen
    -0.76
     VT
    -0.68
    Wilson
    -0.66
     Walsh
    -0.66
     McConnell
    -0.66
    ults
    -0.66
     Hok
    -0.66
    REP
    -0.65
    POSITIVE LOGITS
     diamonds
    3.74
     diamond
    3.64
    iamond
    2.12
    Diamond
    2.07
     Diamond
    1.81
     jewels
    1.72
     platinum
    1.57
     jewel
    1.51
     gems
    1.47
     gem
    1.43
    Activations Density 0.019%

    No Known Activations