Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16224
    Prev
    Next
    INDEX
    Explanations

    mentions of award nominations and wins in various categories such as Best Performance, Best Actor, and others

    oai_token-act-pair · gpt-3.5-turbo

    references to awards and nominations in the context of performances in entertainment

    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
    yip
    -0.79
     routers
    -0.76
     caches
    -0.74
     squats
    -0.73
     tabs
    -0.71
     timers
    -0.71
     tatt
    -0.70
     calcul
    -0.70
     flush
    -0.70
    nings
    -0.69
    POSITIVE LOGITS
     Actress
    1.45
     Drama
    1.32
     Editing
    1.29
     Animated
    1.28
     Supporting
    1.23
     Actor
    1.22
     Feature
    1.20
     Television
    1.19
     screenplay
    1.18
     Film
    1.17
    Activations Density 0.115%

    No Known Activations