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. 10-RES-JB
    6. 15397
    Prev
    Next
    INDEX
    Explanations

    the word "Fast" with varied prefixes and suffixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "fast food" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illary
    -0.79
    pheus
    -0.76
    vironment
    -0.72
    cules
    -0.72
     Marketable
    -0.70
    warts
    -0.69
    xual
    -0.68
    ignty
    -0.68
    arks
    -0.67
     Seym
    -0.67
    POSITIVE LOGITS
    idious
    1.58
     paced
    1.32
    eners
    1.24
    ened
    1.16
    ener
    1.08
    lane
    1.06
    cgi
    1.04
    ening
    1.03
    nesses
    0.96
     asleep
    0.95
    Activations Density 0.028%

    No Known Activations