© 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. 4-RES-JB
    11. 22189
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "origin."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "origin."

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

    No Comments

    Negative Logits
    arnaev
    -0.89
    oaded
    -0.82
    andering
    -0.81
    apter
    -0.78
    kers
    -0.77
    pecting
    -0.77
    EY
    -0.77
    beit
    -0.77
    sol
    -0.73
    elcome
    -0.73
    POSITIVE LOGITS
     Origin
    1.14
     Origins
    0.86
     Radius
    0.85
     Centauri
    0.85
     Advantage
    0.74
     Predator
    0.73
     Austral
    0.72
     Spray
    0.68
     Flav
    0.68
     Ultron
    0.68
    Activations Density 0.013%

    No Known Activations