© 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. 11-RES-JB
    11. 14787
    Prev
    Next
    INDEX
    Explanations

    phrases related to film casting and actor roles

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and their roles in media productions

    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
    devices
    -0.82
    £ı
    -0.80
    matter
    -0.79
    sterdam
    -0.76
     newsletters
    -0.72
     deflation
    -0.70
     caches
    -0.70
     newsletter
    -0.70
     collectors
    -0.69
    INFO
    -0.69
    POSITIVE LOGITS
     actor
    1.50
     actresses
    1.49
     actress
    1.46
     actors
    1.43
     audition
    1.41
     roles
    1.38
     Actor
    1.36
     starring
    1.35
    Actor
    1.33
     Actress
    1.32
    Activations Density 0.693%

    No Known Activations