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. 9-RES-JB
    6. 570
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusivity and equality for all

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity and equality for everyone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
    oute
    -0.68
    potion
    -0.68
    illac
    -0.68
    ifax
    -0.65
     disclaimer
    -0.64
    ernaut
    -0.60
    fman
    -0.60
    plin
    -0.59
    inventoryQuantity
    -0.58
    flation
    -0.58
    POSITIVE LOGITS
     kinds
    1.22
     sorts
    1.19
     stakeholders
    1.06
    ocating
    1.01
     genders
    1.00
    igators
    1.00
     facets
    0.99
    iances
    0.95
     parties
    0.91
     faiths
    0.90
    Activations Density 0.095%

    No Known Activations