© 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. 11-RES-JB
    11. 6478
    Prev
    Next
    INDEX
    Explanations

    words related to confirmations or acknowledgements

    oai_token-act-pair · gpt-3.5-turbo

    topics related to official actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.69
     ILCS
    -0.66
    BuyableInstoreAndOnline
    -0.56
    agogue
    -0.54
    ãĥĩ
    -0.52
    ume
    -0.51
    è¦
    -0.51
    exec
    -0.50
     certific
    -0.50
     Written
    -0.50
    POSITIVE LOGITS
     existed
    1.33
     wasn
    1.28
     was
    1.27
     exists
    1.14
     belonged
    1.09
     hadn
    1.09
    was
    1.04
     wouldn
    1.01
     had
    1.01
     could
    1.01
    Activations Density 0.510%

    No Known Activations