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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 12997
    Prev
    Next
    INDEX
    Explanations

    actions related to combat in gaming contexts

    oai_token-act-pair · gpt-3.5-turbo

    actions related to shooting and competitive gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chens
    -0.80
    ļéĨĴ
    -0.80
    riger
    -0.74
     Webster
    -0.73
     Weiner
    -0.71
    itutional
    -0.71
     Dickinson
    -0.71
    ropolitan
    -0.70
    amaz
    -0.68
     MSNBC
    -0.67
    POSITIVE LOGITS
     respawn
    1.45
     NPCs
    1.27
     teleport
    1.21
     playthrough
    1.20
     quests
    1.18
     melee
    1.14
     gameplay
    1.14
     dungeons
    1.12
     Chocobo
    1.11
     NPC
    1.10
    Activations Density 0.967%

    No Known Activations