© 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. 7880
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that begin with a special character 'Ċ' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the presence of important numerical information or data

    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
     Newsp
    -0.79
     brid
    -0.72
     Scrib
    -0.71
     Sta
    -0.68
     diseng
    -0.66
     Ney
    -0.66
     neighb
    -0.64
     clin
    -0.64
     Seg
    -0.64
     Mothers
    -0.64
    POSITIVE LOGITS
    Reviewed
    1.18
    ³³³
    1.11
    à¨
    0.97
    é»Ĵ
    0.93
    ãĥ¯ãĥ³
    0.92
    ³³³³
    0.91
    Page
    0.90
    CHAPTER
    0.89
    FactoryReloaded
    0.89
    Quantity
    0.88
    Activations Density 0.061%

    No Known Activations