© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1264
    Prev
    Next
    INDEX
    Explanations

    references to technical issues or problems with MacBook Pro computers

    oai_token-act-pair · gpt-3.5-turbo

    references to Apple products, particularly the MacBook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GAN
    -0.70
    ENC
    -0.70
    population
    -0.69
     radiation
    -0.65
     promoter
    -0.64
    vernment
    -0.64
    tein
    -0.62
    ³³³
    -0.61
    Ga
    -0.61
    ground
    -0.61
    POSITIVE LOGITS
     MacBook
    3.72
     Macintosh
    1.75
     macOS
    1.66
     iPod
    1.57
     iPad
    1.45
     iCloud
    1.42
     iPhones
    1.39
     Thunderbolt
    1.35
     iPhone
    1.32
     Chromebook
    1.30
    Activations Density 0.029%

    No Known Activations