© 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. 3-RES-JB
    11. 1856
    Prev
    Next
    INDEX
    Explanations

    social media-related terms like "SHARES" and "Spread"

    oai_token-act-pair · gpt-3.5-turbo

    instances of social media engagement metrics, particularly shares

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tis
    -0.80
    eal
    -0.73
    istically
    -0.73
    oning
    -0.73
    leness
    -0.72
    olog
    -0.70
    onement
    -0.69
    bearing
    -0.69
    grass
    -0.68
    oned
    -0.67
    POSITIVE LOGITS
     SHARES
    1.34
     Tradable
    0.84
    NECT
    0.78
     VIDEOS
    0.75
     Shares
    0.74
     Share
    0.72
     Advertisement
    0.72
    acebook
    0.70
    ileaks
    0.68
     condone
    0.67
    Activations Density 0.007%

    No Known Activations