© 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. 1-RES-JB
    11. 20281
    Prev
    Next
    INDEX
    Explanations

    mentions of computer networks or systems

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "network" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %]
    -0.65
    Adv
    -0.64
    umatic
    -0.62
     hers
    -0.61
    ulhu
    -0.60
    agon
    -0.60
    vent
    -0.60
    olute
    -0.60
    */(
    -0.60
    ric
    -0.59
    POSITIVE LOGITS
     network
    1.27
     networks
    1.22
     Networks
    1.12
    network
    1.03
     connectivity
    0.96
     Network
    0.95
     networking
    0.94
    Network
    0.86
     routers
    0.83
     connections
    0.79
    Activations Density 0.020%

    No Known Activations