© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    promotional phrases related to supporting a cause through financial contributions

    oai_token-act-pair · gpt-3.5-turbo

    references to subscription plans or support requests for journalism

    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
     foreground
    -0.59
     openings
    -0.59
     melting
    -0.58
     Rory
    -0.58
    algia
    -0.58
     sounding
    -0.58
    ovember
    -0.57
     topical
    -0.57
     threads
    -0.57
     thread
    -0.57
    POSITIVE LOGITS
    Bec
    0.84
    Purchase
    0.80
     Upgrade
    0.78
     {*
    0.74
     Simply
    0.71
    Quantity
    0.71
    Alternatively
    0.71
    Upgrade
    0.71
    Choose
    0.68
    $$$$
    0.68
    Activations Density 0.051%

    No Known Activations