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. 11-RES-JB
    6. 17983
    Prev
    Next
    INDEX
    Explanations

    words related to hidden or difficult to find elements in a game context, such as dungeons, bosses, missions, weapons, and upgrades

    oai_token-act-pair · gpt-3.5-turbo

    references to hidden elements and gameplay mechanics in a video game context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ija
    -0.71
    stood
    -0.67
    aughs
    -0.67
    untu
    -0.66
    chin
    -0.65
    ixties
    -0.65
     Baldwin
    -0.65
    1950
    -0.65
     Byrd
    -0.64
    oli
    -0.63
    POSITIVE LOGITS
     NPCs
    1.38
     respawn
    1.36
     quests
    1.32
     mechanic
    1.28
     spawns
    1.26
     unlocks
    1.25
     dungeons
    1.24
     gameplay
    1.23
     unlock
    1.18
     unlocked
    1.18
    Activations Density 0.348%

    No Known Activations