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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2829
    Prev
    Next
    INDEX
    Explanations

    numerical mentions of age

    oai_token-act-pair · gpt-3.5-turbo

    references to age groups related to children and youths

    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
    hyde
    -0.73
     Wast
    -0.72
    ãĤº
    -0.70
    atl
    -0.67
    hof
    -0.67
     unanswered
    -0.63
    sequ
    -0.62
     Byte
    -0.61
     pandemonium
    -0.60
    assian
    -0.60
    POSITIVE LOGITS
     age
    1.36
     ages
    0.99
     65
    0.97
     18
    0.95
     puberty
    0.94
     eighteen
    0.93
    represented
    0.87
     Ages
    0.85
     30
    0.84
     whom
    0.83
    Activations Density 0.102%

    No Known Activations