© 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. 11-RES-JB
    11. 21596
    Prev
    Next
    INDEX
    Explanations

    phrases conveying hope, imagination, and prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express limitation or exclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.64
     Reloaded
    -0.60
    skirts
    -0.59
     clipping
    -0.58
     Morse
    -0.58
    quickShipAvailable
    -0.57
    post
    -0.56
     Dill
    -0.56
    breaks
    -0.56
     Saban
    -0.56
    POSITIVE LOGITS
     speculate
    1.08
     imagine
    0.94
     hope
    0.94
     assume
    0.91
     dream
    0.91
     aspire
    0.90
     afford
    0.87
     conclude
    0.84
     pray
    0.84
     rejoice
    0.79
    Activations Density 0.034%

    No Known Activations