© 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. 20520
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain a period or question mark, indicating the end of statements or questions

    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
     carbohyd
    -1.05
     warr
    -0.93
     affili
    -0.90
     tremend
    -0.85
     finer
    -0.85
     challeng
    -0.83
     confir
    -0.83
     synerg
    -0.82
     stagn
    -0.82
     comple
    -0.81
    POSITIVE LOGITS
     Someone
    1.47
     Called
    1.39
     Suppose
    1.32
     Somebody
    1.31
     Something
    1.25
     Apparently
    1.19
     Specifically
    1.16
     Somewhere
    1.15
     According
    1.11
     Shortly
    1.09
    Activations Density 0.431%

    No Known Activations