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. 10-RES-JB
    6. 14743
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaming, including terms like "weapon," "campaign," "power," and "characters."

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and periods in the context of game mechanics

    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
     institutional
    -0.74
    anson
    -0.73
     booked
    -0.73
     unders
    -0.72
     sweats
    -0.72
     promoter
    -0.71
     formal
    -0.71
     bullish
    -0.71
     certified
    -0.70
     endorsed
    -0.69
    POSITIVE LOGITS
    Players
    1.52
    Gameplay
    1.41
    Characters
    1.36
     Enemies
    1.31
     Players
    1.26
    Spawn
    1.22
    Combat
    1.22
     NPCs
    1.20
    Contents
    1.20
     Alternatively
    1.19
    Activations Density 0.275%

    No Known Activations