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. 10-RES-JB
    6. 169
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming abilities and effects, particularly focused on various forms of damage, impacts on movement speed, and buffs/debuffs

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to game mechanics, particularly damage and stats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.88
    Reviewer
    -0.79
    åŃIJ
    -0.69
    osures
    -0.69
    Redd
    -0.69
     notebooks
    -0.67
    prises
    -0.67
    é¾įå
    -0.66
    eday
    -0.65
    endars
    -0.65
    POSITIVE LOGITS
     Damage
    1.23
     damage
    1.20
     Cooldown
    1.17
     cooldown
    1.13
     Healing
    1.12
     Magicka
    1.09
     healing
    1.08
    Damage
    1.06
     Stamina
    1.06
     dmg
    1.04
    Activations Density 0.090%

    No Known Activations