© 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. 3-RES-JB
    11. 2995
    Prev
    Next
    INDEX
    Explanations

    family-related terms, specifically terms related to parents

    oai_token-act-pair · gpt-3.5-turbo

    references to familial or nurturing figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -1.04
    rawl
    -1.00
    olds
    -0.98
    sburg
    -0.98
    raltar
    -0.92
    reens
    -0.89
    urses
    -0.86
    aith
    -0.86
    rative
    -0.85
    ullivan
    -0.82
    POSITIVE LOGITS
    abwe
    0.90
     Resistance
    0.79
     Ukrain
    0.78
     ration
    0.78
     Shelter
    0.69
     Beware
    0.66
     Despair
    0.66
     Clown
    0.66
     CPI
    0.65
     corrid
    0.65
    Activations Density 0.034%

    No Known Activations