© 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. 1-RES-JB
    11. 2250
    Prev
    Next
    INDEX
    Explanations

    stages of human life, particularly focusing on infancy, adolescence, and adulthood

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stages of human development and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĩ
    -0.80
    ĪĴ
    -0.78
    ²
    -0.73
    Ĥ¬
    -0.73
     deduct
    -0.72
    cedented
    -0.70
    anooga
    -0.68
    ĥ
    -0.68
    ¦
    -0.65
    «ĺ
    -0.65
    POSITIVE LOGITS
    uberty
    1.02
     adulthood
    1.02
     puberty
    0.96
     adolescence
    0.90
     adolesc
    0.89
     ILCS
    0.85
    thood
    0.84
    ipal
    0.80
    framework
    0.75
    amorph
    0.75
    Activations Density 0.032%

    No Known Activations