© 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. 17436
    Prev
    Next
    INDEX
    Explanations

    words related to acting roles or positions in a film or TV show

    oai_token-act-pair · gpt-3.5-turbo

    words related to acting roles and performances in films and television

    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
    £ı
    -0.82
     metabol
    -0.69
    Economic
    -0.67
     newsletters
    -0.67
     disag
    -0.67
     caches
    -0.66
    yip
    -0.66
    arta
    -0.65
    pex
    -0.64
     redist
    -0.64
    POSITIVE LOGITS
    acters
    1.21
     actress
    1.18
     actor
    1.11
     actresses
    1.10
     portraying
    1.10
     starring
    1.06
     audition
    1.06
     actors
    1.06
     portrayal
    1.02
    writer
    1.00
    Activations Density 0.203%

    No Known Activations