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. 1-RES-JB
    6. 3013
    Prev
    Next
    INDEX
    Explanations

    references to bouquets or arrangements of flowers or related items

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "bouquet"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fertility
    -0.72
     cult
    -0.62
     Whitman
    -0.62
     plur
    -0.59
    inki
    -0.57
    Christ
    -0.57
     miscarriage
    -0.57
     qualitative
    -0.57
     Iran
    -0.56
    Virgin
    -0.56
    POSITIVE LOGITS
    quet
    1.41
    eers
    1.08
    arist
    1.02
    atre
    0.96
    eenth
    0.94
    imer
    0.91
    ournament
    0.91
    ball
    0.90
    eting
    0.89
    wright
    0.89
    Activations Density 0.011%

    No Known Activations