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. 3-RES-JB
    6. 11860
    Prev
    Next
    INDEX
    Explanations

    the word "dozens" followed by a number, particularly emphasizing the concept of a large quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dozens."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lover
    -0.69
    ismo
    -0.60
     hegemony
    -0.60
     Correspond
    -0.59
     rapport
    -0.59
     Intent
    -0.57
    MER
    -0.57
    prison
    -0.57
    Dub
    -0.55
    acqu
    -0.55
    POSITIVE LOGITS
    uously
    0.88
     thousand
    0.88
    eenth
    0.87
     thousands
    0.81
    uous
    0.80
    paces
    0.80
    dozen
    0.80
    hovah
    0.79
     dozen
    0.77
     Dozens
    0.75
    Activations Density 0.008%

    No Known Activations