© 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. 10-RES-JB
    11. 5632
    Prev
    Next
    INDEX
    Explanations

    phrases relating to personal experience and emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Salon
    -0.88
     Prohibition
    -0.80
     NYT
    -0.79
     Feminist
    -0.78
    ibrary
    -0.76
     polygamy
    -0.74
     pedoph
    -0.73
     Weinstein
    -0.72
    icist
    -0.70
     Soros
    -0.70
    POSITIVE LOGITS
     congratulate
    1.07
     appreciate
    1.03
     feel
    1.02
     definitely
    1.01
    Coach
    1.00
     hope
    0.99
     bounce
    0.97
    zzo
    0.95
     gotta
    0.94
     cherish
    0.93
    Activations Density 0.246%

    No Known Activations