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. 5898
    Prev
    Next
    INDEX
    Explanations

    instances of the word "precious" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "precious" or variations of it in various contexts

    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
     prep
    -0.65
     factors
    -0.61
     extrap
    -0.61
     Scout
    -0.60
     scout
    -0.59
     pred
    -0.59
     administr
    -0.58
     factor
    -0.58
     Petersen
    -0.57
     administrator
    -0.57
    POSITIVE LOGITS
    cious
    4.95
    conscious
    1.09
    ulously
    1.01
    phy
    0.99
    eous
    0.99
    currency
    0.95
    ciating
    0.94
     Conscious
    0.94
    herent
    0.93
    cedes
    0.93
    Activations Density 0.019%

    No Known Activations