© 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. 0-RES-JB
    11. 17999
    Prev
    Next
    INDEX
    Explanations

    instances of the word "activated."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "activated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uci
    -0.86
     Seym
    -0.84
    bart
    -0.74
    polit
    -0.72
     Wealth
    -0.71
     dow
    -0.70
     Murdoch
    -0.70
    abal
    -0.69
     rake
    -0.69
    jew
    -0.69
    POSITIVE LOGITS
    activated
    3.10
     activated
    2.94
     activate
    1.72
    activate
    1.69
     activating
    1.64
    activation
    1.60
     activates
    1.51
     inactive
    1.47
     activation
    1.47
     responders
    1.36
    Activations Density 0.035%

    No Known Activations