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. 6-RES-JB
    6. 2104
    Prev
    Next
    INDEX
    Explanations

    phrases related to acquiring items or rewards in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    references to game mechanics and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hogan
    -0.87
    ب
    -0.82
     Horton
    -0.78
     Tsarnaev
    -0.77
    ع
    -0.76
     Kuh
    -0.75
     Ferguson
    -0.74
     Trayvon
    -0.74
     photographed
    -0.74
     Carney
    -0.74
    POSITIVE LOGITS
     respawn
    1.24
     quests
    1.22
     teleport
    1.20
     Crafting
    1.19
     NPCs
    1.17
     NPC
    1.16
     potions
    1.15
     Rune
    1.15
     dungeons
    1.13
     Runes
    1.12
    Activations Density 0.628%

    No Known Activations