© 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. 7745
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "family," such as organizations, activities, and individuals connected to family matters

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "family."

    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
    */(
    -0.89
    代
    -0.85
    Downloadha
    -0.81
    psey
    -0.75
    upon
    -0.75
    asar
    -0.69
    eded
    -0.69
    raged
    -0.66
    opping
    -0.66
    realDonaldTrump
    -0.65
    POSITIVE LOGITS
     Families
    1.07
     Family
    0.94
    ilial
    0.91
    ILY
    0.84
     Tree
    0.83
     Matters
    0.83
     Planning
    0.82
     Fathers
    0.82
     Owners
    0.81
     Violence
    0.81
    Activations Density 0.011%

    No Known Activations