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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12128
    Prev
    Next
    INDEX
    Explanations

    references to political and social topics such as ISIS, West, religion, China, Russia, law enforcement, government, and other related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical events, entities, and concepts

    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
    ;;;;
    -0.59
     srf
    -0.53
    senal
    -0.51
    foundland
    -0.50
    jri
    -0.49
    ãĤ´ãĥ³
    -0.49
    ULL
    -0.48
     Leilan
    -0.48
     Azerb
    -0.47
    ilar
    -0.47
    POSITIVE LOGITS
     cannot
    0.65
     should
    0.65
     could
    0.63
     had
    0.60
     can
    0.60
     will
    0.59
     has
    0.58
     hadn
    0.58
     forgot
    0.57
     might
    0.57
    Activations Density 0.901%

    No Known Activations