© 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. 20618
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols at the end of a text segment

    oai_token-act-pair · gpt-3.5-turbo

    instances of articles and references to ongoing stories or important issues

    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
     revol
    -0.82
     challeng
    -0.82
     rhy
    -0.81
     unstoppable
    -0.78
     enthusi
    -0.78
     tremend
    -0.78
     democrat
    -0.78
    ¥ŀ
    -0.77
     paddle
    -0.77
     enriched
    -0.77
    POSITIVE LOGITS
    But
    1.38
    Experts
    1.36
    The
    1.34
    According
    1.33
    However
    1.32
    Asked
    1.31
    Officials
    1.30
    While
    1.29
    It
    1.28
    Among
    1.28
    Activations Density 0.132%

    No Known Activations