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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 18446
    Prev
    Next
    INDEX
    Explanations

    keywords related to mana and cooldown management in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mana management in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sherman
    -0.77
    eday
    -0.76
     Roosevelt
    -0.71
    redd
    -0.70
    çīĪ
    -0.69
    IGH
    -0.69
    rophic
    -0.66
    along
    -0.66
    son
    -0.66
    hood
    -0.65
    POSITIVE LOGITS
     mana
    0.95
     Mana
    0.89
    conservancy
    0.81
    blast
    0.80
     potions
    0.79
     Archdemon
    0.76
     retard
    0.73
    velength
    0.73
    qi
    0.72
     Magicka
    0.71
    Activations Density 0.009%

    No Known Activations