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. 10788
    Prev
    Next
    INDEX
    Explanations

    references to additional content, levels, maps, characters, and gameplay features in video games

    oai_token-act-pair · gpt-3.5-turbo

    references to new features or content in games

    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
    Wikipedia
    -0.83
    Virgin
    -0.79
    Georg
    -0.76
    govtrack
    -0.75
    ertodd
    -0.75
    çͰ
    -0.75
    debian
    -0.75
    Krist
    -0.74
    ittee
    -0.73
    rists
    -0.72
    POSITIVE LOGITS
     quests
    1.35
     dungeons
    1.35
     playable
    1.30
     missions
    1.25
     enemies
    1.24
     bosses
    1.23
     endings
    1.20
     gameplay
    1.20
     costumes
    1.18
     puzzles
    1.17
    Activations Density 0.321%

    No Known Activations