© 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. 10-RES-JB
    11. 16017
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items or actions in various segments of information

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation or phrases indicating a strong conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.85
     challeng
    -0.84
     advoc
    -0.80
     warr
    -0.80
     intermediate
    -0.79
     concess
    -0.79
     carbohyd
    -0.78
    imb
    -0.77
     compr
    -0.77
     encount
    -0.75
    POSITIVE LOGITS
     According
    1.36
     Apparently
    1.26
     Yesterday
    1.22
     Nope
    1.22
     Luckily
    1.20
     Instead
    1.18
     Thankfully
    1.18
     Turns
    1.18
     Consider
    1.16
     Earlier
    1.14
    Activations Density 0.473%

    No Known Activations