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. 12-RES-JB
    6. 17799
    Prev
    Next
    INDEX
    Explanations

    numerical counts or amounts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the occurrence of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    projects
    -1.07
    ooks
    -1.05
    groups
    -1.03
    lations
    -1.02
    estones
    -1.02
    parts
    -0.99
    models
    -0.99
    apers
    -0.98
    sites
    -0.97
    adows
    -0.97
    POSITIVE LOGITS
     hundred
    1.08
     apiece
    1.01
     exception
    0.95
     thousand
    0.94
     dozen
    0.93
     additional
    0.91
     person
    0.91
     ounce
    0.90
     hour
    0.89
     month
    0.87
    Activations Density 0.110%

    No Known Activations