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. 11-RES-JB
    6. 19872
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to the concept of "primary" or "first"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Prim" and its variations, indicating a focus on a specific topic or brand associated with the name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Bard
    -0.70
    IGH
    -0.67
    hold
    -0.62
    lihood
    -0.58
     Moderate
    -0.57
     resolutions
    -0.57
     Graveyard
    -0.57
    人
    -0.56
    hiro
    -0.55
    holding
    -0.55
    POSITIVE LOGITS
    itives
    1.64
    ordial
    1.57
    itive
    1.45
    etime
    1.40
    arily
    1.28
    rose
    1.26
    acy
    1.20
    itiveness
    1.07
    aries
    1.02
    archs
    0.94
    Activations Density 0.036%

    No Known Activations