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. 1178
    Prev
    Next
    INDEX
    Explanations

    various references to different video game characters and terms, potentially related to a specific game or gaming community

    oai_token-act-pair · gpt-3.5-turbo

    terms related to characters and gameplay in video games, particularly focusing on mechanics and items

    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
    amy
    -0.62
     seism
    -0.59
     deaf
    -0.58
    erb
    -0.58
     Marijuana
    -0.57
     Britt
    -0.57
     Gallup
    -0.56
     McCain
    -0.56
     marijuana
    -0.55
     Bradley
    -0.54
    POSITIVE LOGITS
    tein
    0.82
    theless
    0.78
     Chronicles
    0.70
     Nadu
    0.69
     manufact
    0.69
     guid
    0.68
    ragon
    0.65
    agate
    0.64
     Appears
    0.64
     laun
    0.64
    Activations Density 0.319%

    No Known Activations