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. 15616
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly with a focus on object-oriented languages and education in computing

    oai_token-act-pair · gpt-3.5-turbo

    references to role-playing games and their associated mechanics

    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
    ãģ®å®
    -0.66
     nort
    -0.63
    ãģ®éŃĶ
    -0.60
     Helic
    -0.58
    inx
    -0.57
     pent
    -0.57
     oats
    -0.57
     pist
    -0.57
     submer
    -0.57
     mast
    -0.56
    POSITIVE LOGITS
    specific
    1.14
    seeking
    0.97
    centric
    0.96
    wise
    0.95
    laden
    0.95
    related
    0.94
    management
    0.91
    based
    0.90
    driven
    0.89
    sized
    0.88
    Activations Density 0.101%

    No Known Activations