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

    Neuronpedia

    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. 7-RES-JB
    11. 23025
    Prev
    Next
    INDEX
    Explanations

    references to cartoon characters

    oai_token-act-pair · gpt-3.5-turbo

    references to cartoons and animated characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opio
    -0.71
     sclerosis
    -0.71
    vae
    -0.70
    govern
    -0.65
    SPONSORED
    -0.64
    acia
    -0.63
    ructure
    -0.61
    foreseen
    -0.61
    Availability
    -0.59
    HI
    -0.58
    POSITIVE LOGITS
    ishly
    1.11
     cartoons
    1.04
    ists
    1.01
     cartoon
    0.94
    ist
    0.92
    oons
    0.89
    ish
    0.88
    enegger
    0.87
     caric
    0.86
    istically
    0.85
    Activations Density 0.035%

    No Known Activations