© 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. 9-RES-JB
    11. 13927
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or social activism

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, particularly periods, indicating the conclusion of thoughts

    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
    Reply
    -0.76
     independ
    -0.73
    è¦ļéĨĴ
    -0.71
     tremend
    -0.68
    âĸ¬âĸ¬
    -0.67
    RAW
    -0.64
     ont
    -0.61
    yip
    -0.60
     Âł Âł Âł Âł
    -0.60
    =-=-=-=-=-=-=-=-
    -0.60
    POSITIVE LOGITS
    ↵
    1.13
     Instead
    0.98
     And
    0.95
     But
    0.91
     Turns
    0.89
     Thousands
    0.88
     Dozens
    0.88
     Months
    0.87
     Though
    0.86
     Along
    0.84
    Activations Density 0.551%

    No Known Activations