© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7591
    Prev
    Next
    INDEX
    Explanations

    mentions of the messaging application WhatsApp

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the WhatsApp application and its related features

    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
    ©¶æ
    -0.87
    gling
    -0.81
    iverpool
    -0.78
    opez
    -0.75
    herty
    -0.75
    arson
    -0.74
    gio
    -0.73
    abama
    -0.70
    ibli
    -0.70
    arde
    -0.69
    POSITIVE LOGITS
     Messenger
    0.96
     messaging
    0.88
     messenger
    0.87
    Secure
    0.86
     subscriptions
    0.83
    Chat
    0.83
     Messages
    0.82
     Users
    0.80
    ipop
    0.79
     chats
    0.79
    Activations Density 0.060%

    No Known Activations