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. 8-RES-JB
    6. 15369
    Prev
    Next
    INDEX
    Explanations

    references to specific video game titles within the Grand Theft Auto and Call of Duty franchises

    oai_token-act-pair · gpt-3.5-turbo

    references to popular video game franchises and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rist
    -0.77
    umbn
    -0.76
    Reviewer
    -0.75
     eleph
    -0.75
    upper
    -0.72
    uckland
    -0.72
    abo
    -0.71
    shr
    -0.70
    wa
    -0.69
    lace
    -0.68
    POSITIVE LOGITS
    âĦ¢:
    1.11
    ®
    0.98
     Remastered
    0.95
     III
    0.94
     Multiplayer
    0.92
     Trilogy
    0.91
    âĦ¢
    0.90
     ®
    0.90
     multiplayer
    0.88
     Primal
    0.87
    Activations Density 0.133%

    No Known Activations