Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 641
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a punctuation mark, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Period at the end of sentences declaring something about the world.

    Explanation Uploaded by User
    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
     corrid
    -0.90
     advoc
    -0.89
     glim
    -0.87
     advis
    -0.86
     tradem
    -0.84
     calming
    -0.80
     encount
    -0.80
     enthusi
    -0.80
     reluct
    -0.80
     volunte
    -0.78
    POSITIVE LOGITS
     Therefore
    1.83
     Hence
    1.61
     Consequently
    1.61
     Furthermore
    1.58
     Moreover
    1.55
     Thus
    1.53
     Secondly
    1.47
     Likewise
    1.46
     And
    1.41
     Anything
    1.41
    Activations Density 0.428%

    No Known Activations