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. 11-RES-JB
    6. 15427
    Prev
    Next
    INDEX
    Explanations

    terms related to different kinds of metals and minerals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to minerals and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Volunteers
    -0.87
     Refugee
    -0.86
     Huckabee
    -0.81
     Patient
    -0.80
     Priebus
    -0.80
    Bus
    -0.79
     Nurse
    -0.78
     Homeless
    -0.76
     Duffy
    -0.76
    EStreamFrame
    -0.75
    POSITIVE LOGITS
     quartz
    1.77
     diamonds
    1.70
     alloy
    1.63
     minerals
    1.62
     diamond
    1.59
     metals
    1.57
     titanium
    1.56
     granite
    1.52
     stones
    1.50
     quar
    1.48
    Activations Density 0.331%

    No Known Activations