© 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. 2-RES-JB
    11. 11766
    Prev
    Next
    INDEX
    Explanations

    descriptions or actions related to infants or very young children

    oai_token-act-pair · gpt-3.5-turbo

    references to toddlers and related parenting concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rity
    -0.80
    irin
    -0.73
    sts
    -0.71
    idable
    -0.69
    roots
    -0.68
    apego
    -0.67
    vernment
    -0.67
    ibal
    -0.66
    actionDate
    -0.65
    reens
    -0.65
    POSITIVE LOGITS
     toddler
    1.04
     toddlers
    0.85
    hesis
    0.82
    ishly
    0.79
     tant
    0.73
     todd
    0.72
    hetical
    0.72
    pole
    0.70
     diaper
    0.68
     Claus
    0.67
    Activations Density 0.016%

    No Known Activations