© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21041
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms and activities like posting, commenting, or sharing

    oai_token-act-pair · gpt-3.5-turbo

    references to posting on social media platforms, particularly Facebook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.72
    mentation
    -0.67
    fts
    -0.65
    sen
    -0.62
    oso
    -0.62
    rica
    -0.62
    abe
    -0.60
    apy
    -0.59
    ]=
    -0.59
    ppo
    -0.59
    POSITIVE LOGITS
    ulate
    1.06
     flyers
    1.02
     selfies
    1.01
     pics
    0.98
     pictures
    0.96
     screenshots
    0.92
     photos
    0.91
     videos
    0.88
    hum
    0.87
     anonymously
    0.85
    Activations Density 0.062%

    No Known Activations