© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10793
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming and character attributes like health, attack, defense, and damage values

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to character statistics in a game

    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
    ovie
    -0.75
    soDeliveryDate
    -0.75
    Commercial
    -0.74
    orld
    -0.73
     Hirosh
    -0.73
     Bellev
    -0.73
     Helsinki
    -0.72
     Klu
    -0.72
     Kinn
    -0.71
     photographed
    -0.71
    POSITIVE LOGITS
     modifier
    1.33
     modifiers
    1.28
     bonuses
    1.22
     cooldown
    1.17
     bonus
    1.16
     dmg
    1.14
     regeneration
    1.12
     multiplier
    1.11
     damage
    1.10
     orbs
    1.09
    Activations Density 0.160%

    No Known Activations