© 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. 11-RES-JB
    11. 21227
    Prev
    Next
    INDEX
    Explanations

    network-related terms like IP address and TCP connection

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to networking and data transmission

    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
    Batman
    -0.90
    Bat
    -0.87
     Nib
    -0.83
    Bir
    -0.83
     Calvin
    -0.82
     Asuka
    -0.81
     Harley
    -0.79
     Candy
    -0.77
    Pal
    -0.77
     Cabrera
    -0.74
    POSITIVE LOGITS
     IPv
    1.98
     DHCP
    1.97
     routers
    1.65
     router
    1.63
     DNS
    1.61
     Router
    1.60
     NAT
    1.55
     Ethernet
    1.54
     TCP
    1.50
     UDP
    1.49
    Activations Density 0.373%

    No Known Activations