© 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. 7-RES-JB
    11. 1703
    Prev
    Next
    INDEX
    Explanations

    terms related to pop culture and modern technology

    oai_token-act-pair · gpt-3.5-turbo

    references to pop culture, particularly involving movies and video games

    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
    ¿½
    -0.94
     confidentiality
    -0.71
    PsyNetMessage
    -0.71
     Marketable
    -0.70
     omission
    -0.66
     experien
    -0.63
     Ples
    -0.63
     ESV
    -0.61
     workings
    -0.60
     pregn
    -0.60
    POSITIVE LOGITS
    ultural
    0.87
    arts
    0.79
    grain
    0.78
    culture
    0.75
    Americ
    0.75
    pocket
    0.74
    agall
    0.73
    African
    0.73
    raltar
    0.73
    sav
    0.72
    Activations Density 0.127%

    No Known Activations