© 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. 14695
    Prev
    Next
    INDEX
    Explanations

    technical terms related to a specific technology or product called "Fusion."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Fusion" or related terms in various contexts

    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
    ript
    -0.77
    cott
    -0.77
     livest
    -0.72
     Logged
    -0.72
    #$#$
    -0.69
    obby
    -0.68
    Org
    -0.68
    ask
    -0.67
    ufact
    -0.66
    anty
    -0.65
    POSITIVE LOGITS
     Fusion
    0.83
    ãĥ¼ãĤ¯
    0.77
    emonium
    0.71
    itiveness
    0.70
     capacitor
    0.68
    ctions
    0.68
    itive
    0.68
     Twins
    0.68
    atorium
    0.68
    ibles
    0.67
    Activations Density 0.031%

    No Known Activations