© 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. 6-RES-JB
    11. 19816
    Prev
    Next
    INDEX
    Explanations

    technology-related keywords or phrases such as "browser", "phone", "tablet", "computer", "laptop", "cable", "TV", "web", "library card", and "satellite"

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and devices

    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
     Canaver
    -0.68
     Turks
    -0.68
     Ramos
    -0.65
    baugh
    -0.65
    auld
    -0.62
     Kinn
    -0.62
    hig
    -0.61
     Slovenia
    -0.60
    witz
    -0.60
     McGr
    -0.60
    POSITIVE LOGITS
     selves
    0.94
     mates
    0.79
     spouse
    0.74
     buddy
    0.72
     mate
    0.72
    mate
    0.70
    heit
    0.70
    mates
    0.70
     roommate
    0.68
     buddies
    0.68
    Activations Density 0.318%

    No Known Activations