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. 15549
    Prev
    Next
    INDEX
    Explanations

    ages of individuals, particularly children

    oai_token-act-pair · gpt-3.5-turbo

    age ranges and references to children

    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
    ãĥī
    -0.65
     Profit
    -0.62
     CLIENT
    -0.62
     restoration
    -0.62
    soType
    -0.61
     conduc
    -0.60
    NetMessage
    -0.60
     seq
    -0.59
     Restaur
    -0.58
     capitalists
    -0.58
    POSITIVE LOGITS
     preschool
    1.40
     toddlers
    1.28
     kindergarten
    1.24
     kinderg
    1.24
     toddler
    1.19
    chool
    1.11
     ages
    1.09
     puberty
    1.08
     youngest
    1.03
     teenager
    1.03
    Activations Density 0.378%

    No Known Activations