© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 18508
    Prev
    Next
    INDEX
    Explanations

    instances where sentences end with punctuation, specifically periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period, indicating complete thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awaited
    -0.75
     alleged
    -0.75
    iannopoulos
    -0.75
     millenn
    -0.74
     hailed
    -0.73
     descendants
    -0.73
     imprisoned
    -0.72
     detained
    -0.72
     unspecified
    -0.71
     unmanned
    -0.70
    POSITIVE LOGITS
     Ideally
    1.42
     Avoid
    1.34
     Remember
    1.30
     Knowing
    1.27
     Especially
    1.27
    Avoid
    1.27
     Include
    1.27
     Often
    1.26
     Always
    1.22
     Lastly
    1.22
    Activations Density 0.511%

    No Known Activations