© 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. 17584
    Prev
    Next
    INDEX
    Explanations

    phrases related to family members, especially parental figures

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and roles

    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
    ways
    -0.80
    ser
    -0.76
    COL
    -0.74
    Edited
    -0.74
    sed
    -0.74
    ivities
    -0.73
    sports
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    susp
    -0.68
    binding
    -0.68
    POSITIVE LOGITS
    apa
    1.13
     Papa
    1.12
     Mama
    1.04
    ciating
    0.84
    uppet
    0.83
    omo
    0.82
    emonic
    0.79
    arella
    0.77
     Romeo
    0.75
     Panda
    0.74
    Activations Density 0.013%

    No Known Activations