© 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. 4-RES-JB
    11. 13304
    Prev
    Next
    INDEX
    Explanations

    references to internet memes

    oai_token-act-pair · gpt-3.5-turbo

    references to memes and related cultural phenomena

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

    No Comments

    Negative Logits
     Thro
    -0.74
     charism
    -0.67
    avid
    -0.64
    arta
    -0.64
    hani
    -0.63
     glim
    -0.63
     Yards
    -0.61
     negotiator
    -0.61
    enting
    -0.61
    yer
    -0.60
    POSITIVE LOGITS
     memes
    1.07
     meme
    0.99
    bers
    0.83
    pty
    0.78
    isphere
    0.73
    ery
    0.71
    iverse
    0.71
    imedia
    0.71
    etically
    0.70
    oji
    0.69
    Activations Density 0.012%

    No Known Activations