© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 9304
    Prev
    Next
    INDEX
    Explanations

    phrases related to family and personal life experiences, particularly emotional situations

    oai_token-act-pair · gpt-3.5-turbo

    sentiments and expressions of emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aggregate
    -0.79
     obsolete
    -0.78
     antitrust
    -0.72
     attribution
    -0.71
    ivably
    -0.71
    thal
    -0.70
     assemble
    -0.69
     coales
    -0.69
     interoper
    -0.69
    buster
    -0.69
    POSITIVE LOGITS
    Parents
    1.18
    Doctors
    0.97
    Family
    0.95
     pregnancies
    0.94
     Parents
    0.94
    Dad
    0.87
    Teen
    0.87
    parents
    0.86
    husband
    0.85
    Friends
    0.85
    Activations Density 1.065%

    No Known Activations