© 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. 9-RES-JB
    11. 7437
    Prev
    Next
    INDEX
    Explanations

    specific names and titles of high-profile individuals, especially CEOs

    oai_token-act-pair · gpt-3.5-turbo

    prominent business figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.74
     festive
    -0.70
     Incarnation
    -0.64
     offences
    -0.63
    girl
    -0.63
    resy
    -0.62
     gard
    -0.61
     Korra
    -0.61
     neighbourhoods
    -0.59
     playthrough
    -0.59
    POSITIVE LOGITS
     Soros
    1.05
     Goldman
    1.04
     Brookings
    1.00
     Rockefeller
    0.99
     Sachs
    0.99
     Exxon
    0.97
    kefeller
    0.97
     billionaires
    0.92
     Economist
    0.92
     Kissinger
    0.91
    Activations Density 0.761%

    No Known Activations