© 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. 8-RES-JB
    11. 17772
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with periods, indicating the end of statements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deity
    -0.86
     initials
    -0.83
     blasp
    -0.79
     aven
    -0.77
     referee
    -0.75
     intruder
    -0.74
     interrog
    -0.73
     guardian
    -0.73
     silent
    -0.73
     optional
    -0.72
    POSITIVE LOGITS
     Increasing
    1.33
     Estimates
    1.26
     Consequently
    1.24
     Meanwhile
    1.24
     Whereas
    1.19
     Unemployment
    1.17
     Recent
    1.17
    Incre
    1.16
     Compared
    1.15
     Indeed
    1.15
    Activations Density 0.488%

    No Known Activations