© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    social media apps

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the messaging application WhatsApp

    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
    ci
    -0.83
    ively
    -0.68
    irk
    -0.68
    ura
    -0.63
    uct
    -0.63
     interpreted
    -0.62
    ado
    -0.62
    eline
    -0.62
     honored
    -0.61
    ae
    -0.61
    POSITIVE LOGITS
     Whats
    4.20
     whats
    2.17
     Lets
    1.37
     Pastebin
    1.29
    yip
    1.15
     thats
    1.06
     WhatsApp
    1.00
    20439
    0.99
     VK
    0.98
     wast
    0.98
    Activations Density 0.029%

    No Known Activations