© 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. 23014
    Prev
    Next
    INDEX
    Explanations

    mentions of wealthy individuals or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to wealthy individuals and their influence

    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
    uality
    -0.86
    uberty
    -0.79
    DOC
    -0.76
    nant
    -0.74
    pty
    -0.72
    CDC
    -0.69
    otide
    -0.69
    urgy
    -0.69
    ppa
    -0.66
    PRESS
    -0.66
    POSITIVE LOGITS
     earners
    0.96
     donors
    0.86
     holdings
    0.86
     philanthrop
    0.85
     Institution
    0.82
     landowners
    0.79
     Asians
    0.78
     businessmen
    0.74
    lier
    0.74
     elites
    0.74
    Activations Density 0.039%

    No Known Activations