© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    instances where the text is marked or formatted in a specific way (e.g., symbols or characters representing a particular style)

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or developments

    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
     tram
    -0.79
     swall
    -0.77
    ©¶æ
    -0.74
     veter
    -0.72
     disciplines
    -0.72
     trump
    -0.70
     license
    -0.70
     therm
    -0.70
     behaviors
    -0.69
     dece
    -0.68
    POSITIVE LOGITS
    According
    1.30
    However
    1.27
    Since
    1.26
    Meanwhile
    1.26
    While
    1.26
    Speaking
    1.26
    Indeed
    1.23
    Among
    1.23
    Others
    1.23
    But
    1.22
    Activations Density 0.304%

    No Known Activations