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. 7-RES-JB
    6. 1071
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or simultaneity, especially with terms like "as," "well," "to," and "next to."

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate conditions or features of elements in a description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.80
    IDs
    -0.63
    itte
    -0.63
    alde
    -0.59
     seiz
    -0.58
     Nig
    -0.58
    OPLE
    -0.58
    appers
    -0.57
    ppo
    -0.57
    mone
    -0.56
    POSITIVE LOGITS
    between
    0.78
     reminiscent
    0.73
    rium
    0.70
     culminating
    0.67
    urring
    0.66
     akin
    0.66
    which
    0.64
     which
    0.62
     accompanies
    0.61
     headlined
    0.61
    Activations Density 0.677%

    No Known Activations