© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    business partnerships or collaborations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "partnership" and related terms

    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
    gun
    -0.80
    akia
    -0.75
    gor
    -0.72
    hma
    -0.72
    itri
    -0.70
    metics
    -0.69
    cho
    -0.69
    raq
    -0.68
    leigh
    -0.67
    bern
    -0.66
    POSITIVE LOGITS
     between
    1.09
     partner
    0.99
     agreement
    0.90
     partners
    0.89
    SHIP
    0.89
     BET
    0.88
     partnership
    0.87
     partnerships
    0.85
     agreements
    0.83
     arrangement
    0.80
    Activations Density 0.090%

    No Known Activations