© 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. 13913
    Prev
    Next
    INDEX
    Explanations

    references to teenage mutant ninja turtles

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Teenage Mutant Ninja Turtles" franchise and associated media

    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
    xual
    -0.88
     intrins
    -0.73
    mble
    -0.72
    sels
    -0.72
     locality
    -0.64
     needles
    -0.63
    itsch
    -0.63
    icago
    -0.63
    bnb
    -0.62
     deed
    -0.62
    POSITIVE LOGITS
     Turtles
    1.04
    agers
    0.94
    age
    0.93
     Titans
    0.86
     Turtle
    0.78
    eteen
    0.77
     Cyborg
    0.74
     Panel
    0.73
    ety
    0.73
    boss
    0.72
    Activations Density 0.057%

    No Known Activations