© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14013
    Prev
    Next
    INDEX
    Explanations

    references to age, specifically children of varying ages

    oai_token-act-pair · gpt-3.5-turbo

    references to children and their ages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Restaur
    -0.77
     employers
    -0.71
     capitalists
    -0.71
     collaborators
    -0.71
    ablishment
    -0.68
     Lobby
    -0.66
     Employee
    -0.65
     offices
    -0.64
     profitability
    -0.64
     reven
    -0.64
    POSITIVE LOGITS
     preschool
    1.36
     toddlers
    1.35
     toddler
    1.30
     kindergarten
    1.25
     kinderg
    1.19
     puberty
    1.17
     ages
    1.14
    chool
    1.13
     youngster
    1.10
     infants
    1.10
    Activations Density 0.517%

    No Known Activations