© 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. 2-RES-JB
    11. 6555
    Prev
    Next
    INDEX
    Explanations

    phrases related to "My Little Pony" characters and themes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "My Little Pony" franchise and its characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.87
    INST
    -0.74
     Judgment
    -0.68
    SPONSORED
    -0.67
    Oracle
    -0.66
    WINDOWS
    -0.66
    enance
    -0.64
    scape
    -0.64
    Glass
    -0.63
    HER
    -0.62
    POSITIVE LOGITS
     pony
    1.05
     ponies
    0.96
     Sparkle
    0.96
     Pony
    0.91
    tail
    0.88
     Canter
    0.83
    atron
    0.81
    enhagen
    0.80
    tailed
    0.78
    utical
    0.78
    Activations Density 0.015%

    No Known Activations