© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    punctuation marks with a focus on periods

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
     brill
    -0.79
     nodd
    -0.75
    abouts
    -0.74
     gobl
    -0.72
    ŃĶ
    -0.72
     tradem
    -0.71
     babe
    -0.70
     canv
    -0.70
     congr
    -0.67
     enthusi
    -0.67
    POSITIVE LOGITS
     Consequently
    1.72
     Thus
    1.63
     Such
    1.58
     Conversely
    1.58
     This
    1.56
     Furthermore
    1.55
     Moreover
    1.53
     Hence
    1.53
     Therefore
    1.49
     These
    1.48
    Activations Density 0.389%

    No Known Activations