Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15994
    Prev
    Next
    INDEX
    Explanations

    references to the messaging service "WhatsApp"

    oai_token-act-pair · gpt-3.5-turbo

    references to messaging applications, particularly WhatsApp and Telegram

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gling
    -1.11
    enhagen
    -0.83
    usive
    -0.83
    ocrine
    -0.80
    este
    -0.79
    arson
    -0.76
    bard
    -0.75
    amily
    -0.75
    ©¶æ
    -0.74
    gio
    -0.74
    POSITIVE LOGITS
    ILA
    0.83
     Messenger
    0.73
     messenger
    0.70
     Hots
    0.70
    room
    0.68
    rooms
    0.67
    CHAT
    0.66
     Telegram
    0.65
     CLSID
    0.64
     Magnum
    0.64
    Activations Density 0.053%

    No Known Activations