© 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. 3-RES-JB
    11. 1789
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of being "wired" for something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "wired" or connected, both in a physical and metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vic
    -0.78
    imates
    -0.73
    anches
    -0.66
    mol
    -0.65
    imated
    -0.65
    execute
    -0.65
    Brave
    -0.64
    iva
    -0.63
    adier
    -0.63
    76561
    -0.63
    POSITIVE LOGITS
     wired
    1.18
    wired
    1.12
     wiring
    0.96
    creen
    0.89
     circuitry
    0.83
     Ethernet
    0.82
     connectivity
    0.78
    nesday
    0.77
    oreal
    0.77
    hester
    0.77
    Activations Density 0.008%

    No Known Activations