© 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. 9-RES-JB
    11. 15674
    Prev
    Next
    INDEX
    Explanations

    IP addresses and network-related terms and settings

    oai_token-act-pair · gpt-3.5-turbo

    networking and communication protocols, particularly in the context of IP addresses and port settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.86
     [&
    -0.72
     exerc
    -0.70
     infographic
    -0.67
     accompanying
    -0.65
    ensation
    -0.65
     reactive
    -0.65
     supplement
    -0.64
    matic
    -0.64
     Orn
    -0.63
    POSITIVE LOGITS
    addr
    1.06
    host
    1.05
    password
    1.01
    domain
    1.00
    localhost
    0.99
    Host
    0.94
    username
    0.94
    raltar
    0.87
    prefix
    0.87
    192
    0.86
    Activations Density 0.112%

    No Known Activations