© 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. 8-RES-JB
    11. 2724
    Prev
    Next
    INDEX
    Explanations

    sources or references mentioned in a given text

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or publications in articles

    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
    externalActionCode
    -0.64
     numbering
    -0.64
    merce
    -0.63
    $$$$
    -0.63
    oster
    -0.62
    FORE
    -0.62
    ij士
    -0.62
     satell
    -0.62
     Skydragon
    -0.61
     sole
    -0.59
    POSITIVE LOGITS
    facebook
    0.78
    erous
    0.76
     Videos
    0.72
     Coverage
    0.67
    tight
    0.67
     McA
    0.66
     Photos
    0.66
     Video
    0.65
     VICE
    0.64
    related
    0.63
    Activations Density 0.090%

    No Known Activations