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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19390
    Prev
    Next
    INDEX
    Explanations

    words related to superhero stories and battles

    oai_token-act-pair · gpt-3.5-turbo

    narrative elements related to family dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coverage
    -0.73
     Carney
    -0.71
    espie
    -0.71
    displayText
    -0.71
     MSNBC
    -0.68
     Zucker
    -0.66
    verage
    -0.64
    National
    -0.64
     CNBC
    -0.64
     endorsements
    -0.64
    POSITIVE LOGITS
     Berserker
    0.95
     sorce
    0.95
     teleportation
    0.94
     armor
    0.93
     Norn
    0.93
     goblin
    0.92
     cursed
    0.92
     teleport
    0.91
     mage
    0.90
     enchantment
    0.90
    Activations Density 1.376%

    No Known Activations