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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9528
    Prev
    Next
    INDEX
    Explanations

    mentions of messaging services and related features

    oai_token-act-pair · gpt-3.5-turbo

    references to messaging services and their features

    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
    OIL
    -0.91
    Disney
    -0.82
    aez
    -0.79
    arson
    -0.75
    nyder
    -0.74
     bulldo
    -0.74
    aterasu
    -0.74
    chwitz
    -0.73
    owicz
    -0.72
    jandro
    -0.71
    POSITIVE LOGITS
     Telegram
    2.31
     messaging
    1.92
     Messenger
    1.92
     WhatsApp
    1.87
     Messages
    1.73
     chat
    1.68
     Chat
    1.67
    legram
    1.65
     chats
    1.64
    Chat
    1.63
    Activations Density 0.274%

    No Known Activations