© 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. 11466
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements that end with a period

    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
    -0.91
    ŃĶ
    -0.86
     teasp
    -0.74
     exha
    -0.72
     glim
    -0.72
     explan
    -0.69
    ometimes
    -0.69
     ingred
    -0.68
     psychiat
    -0.67
     unden
    -0.67
    POSITIVE LOGITS
     Similarly
    1.46
     Another
    1.37
    <|endoftext|>
    1.36
     Likewise
    1.34
     Also
    1.31
    ↵
    1.28
     Additionally
    1.28
     Lastly
    1.23
     Alternatively
    1.23
     Meanwhile
    1.20
    Activations Density 0.505%

    No Known Activations