© 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. 11-RES-JB
    11. 2021
    Prev
    Next
    INDEX
    Explanations

    references to numerical information or statistical data

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements that convey uncertainty or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.79
     proport
    -0.78
     exha
    -0.67
     occas
    -0.66
     eleph
    -0.63
    aditional
    -0.63
     footing
    -0.61
     authentic
    -0.61
     belonging
    -0.61
     engagements
    -0.60
    POSITIVE LOGITS
    advertisement
    0.99
    ³³³³³³³³
    0.98
    posted
    0.92
    ³³³³
    0.90
    ³³³
    0.86
    ³³³³³³³³³³³³³³³³
    0.86
    Advertisement
    0.82
    Anyway
    0.81
    Posted
    0.80
    Article
    0.79
    Activations Density 0.499%

    No Known Activations