© 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. 22240
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters in movies and TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television and film characters and roles

    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
    policy
    -0.74
    articles
    -0.74
    âķIJâķIJ
    -0.73
     RELEASE
    -0.71
    ISO
    -0.69
    INFO
    -0.68
     enrichment
    -0.65
    project
    -0.65
    Companies
    -0.65
    Fine
    -0.63
    POSITIVE LOGITS
     protagonist
    1.12
     portrayed
    1.06
     villain
    1.04
     antagonist
    1.00
     narrator
    0.95
     voiced
    0.94
     character
    0.85
     archetype
    0.83
     alongside
    0.82
    agonist
    0.82
    Activations Density 0.297%

    No Known Activations