© 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. 567
    Prev
    Next
    INDEX
    Explanations

    words related to providing or offering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "provided."

    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
    focus
    -0.82
    Boss
    -0.80
    MAT
    -0.79
    mat
    -0.76
    can
    -0.73
    boss
    -0.73
    do
    -0.72
    Rated
    -0.70
    ener
    -0.70
    thin
    -0.69
    POSITIVE LOGITS
    utical
    0.92
     sust
    0.80
     showc
    0.80
     refunds
    0.73
     generously
    0.72
     condolences
    0.72
     supplied
    0.72
    Ö¼
    0.72
     deliveries
    0.70
     pertinent
    0.69
    Activations Density 0.033%

    No Known Activations