© 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. 9-RES-JB
    11. 10054
    Prev
    Next
    INDEX
    Explanations

    actor names and their roles in movies or TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and their roles in film or theater productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newsletters
    -0.90
    pour
    -0.85
    wcs
    -0.83
     VIDEOS
    -0.80
    useum
    -0.75
    Spread
    -0.75
     juices
    -0.74
    atories
    -0.74
    foundation
    -0.73
    Statistics
    -0.73
    POSITIVE LOGITS
     narrator
    1.01
     protagonist
    0.99
     villain
    0.94
     Sheriff
    0.93
     Agent
    0.93
     antagonist
    0.90
     Captain
    0.85
     Troy
    0.85
     Lucy
    0.84
     Robbie
    0.84
    Activations Density 0.104%

    No Known Activations