© 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. 1-RES-JB
    11. 9388
    Prev
    Next
    INDEX
    Explanations

    words related to computer networks and technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Network."

    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
    uations
    -0.70
    gg
    -0.70
    ppy
    -0.69
    ques
    -0.67
    sql
    -0.66
    ampunk
    -0.64
    gets
    -0.64
    trump
    -0.64
    orate
    -0.63
    manuel
    -0.62
    POSITIVE LOGITS
     Network
    1.23
     Networks
    1.17
     network
    0.97
    network
    0.95
     networks
    0.95
     Tycoon
    0.88
    Network
    0.84
     Connection
    0.83
    edIn
    0.78
     Broadcast
    0.77
    Activations Density 0.007%

    No Known Activations