© 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. 8-RES-JB
    11. 7818
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with 'we'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive pronouns and collective language indicating inclusion or teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forms
    -0.67
     Organizations
    -0.59
     Rarity
    -0.59
     Authority
    -0.57
     Oprah
    -0.56
     Commissioner
    -0.56
    whel
    -0.55
    âĢ¢âĢ¢
    -0.55
     gratification
    -0.55
     Coalition
    -0.54
    POSITIVE LOGITS
    ighed
    1.09
    arers
    1.05
     assume
    1.00
    eding
    0.96
    're
    0.96
     ourselves
    0.96
    aning
    0.95
    athered
    0.94
    've
    0.92
    igh
    0.92
    Activations Density 0.187%

    No Known Activations