© 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. 20859
    Prev
    Next
    INDEX
    Explanations

    words related to greetings

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to greetings

    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
    negie
    -0.78
    ulz
    -0.68
    proxy
    -0.68
    uld
    -0.66
    cano
    -0.65
    aq
    -0.65
    icum
    -0.65
     inhibitors
    -0.63
     inhibitor
    -0.63
    eki
    -0.63
    POSITIVE LOGITS
     greet
    1.20
     greeting
    1.15
     greets
    0.94
     greeted
    0.90
    enance
    0.85
     hello
    0.82
     goodbye
    0.82
    reetings
    0.79
    prise
    0.78
    mallow
    0.78
    Activations Density 0.019%

    No Known Activations