© 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. 6-RES-JB
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses ending in punctuation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quir
    -0.77
    ©¶æ¥µ
    -0.71
    ©¶æ
    -0.69
     temperament
    -0.67
     affili
    -0.65
    emaker
    -0.64
     occupation
    -0.62
    ŃĶ
    -0.62
     impression
    -0.62
     assault
    -0.61
    POSITIVE LOGITS
     However
    1.20
     Especially
    1.16
     Whilst
    1.15
     Unfortunately
    1.10
     Specifically
    1.10
     Additionally
    1.06
     Thankfully
    1.02
     Luckily
    1.01
     Typically
    1.01
     Besides
    1.01
    Activations Density 0.667%

    No Known Activations