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

    Neuronpedia

    Jacobian LensNEW
    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. 3388
    Prev
    Next
    INDEX
    Explanations

    age-related information about early life events

    oai_token-act-pair · gpt-3.5-turbo

    references to age, particularly when discussing significant life events during childhood or adolescence

    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
    sonian
    -0.72
    ãĤ´ãĥ³
    -0.69
    Ô
    -0.64
    oreal
    -0.59
     intensify
    -0.59
     SetTextColor
    -0.59
     compromises
    -0.58
    ãĥ¼ãĤ¯
    -0.58
    ãĥ¡
    -0.58
    ãĥ¼ãĥ³
    -0.58
    POSITIVE LOGITS
     younger
    1.31
     young
    1.15
     teenager
    1.10
     undergrad
    1.05
     teens
    1.03
     teenagers
    1.01
     kid
    0.98
     youth
    0.96
     youngster
    0.93
     toddlers
    0.93
    Activations Density 0.091%

    No Known Activations