© 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. 11441
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuations

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that conclude or summarize information

    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
     blush
    -0.85
     challeng
    -0.77
     chopping
    -0.73
     butcher
    -0.73
     ageing
    -0.70
     arsen
    -0.69
     mummy
    -0.68
     demos
    -0.68
     choke
    -0.67
     chimpanzees
    -0.66
    POSITIVE LOGITS
    com
    1.76
    biz
    1.40
    org
    1.37
    net
    1.31
    tv
    1.25
    co
    1.24
    info
    1.16
    cn
    1.14
    ca
    1.14
    fm
    1.11
    Activations Density 0.075%

    No Known Activations