© 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. 0-RES-JB
    11. 1751
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    walk
    -0.77
    clone
    -0.72
    lessness
    -0.69
    boat
    -0.62
     Gets
    -0.62
    verts
    -0.60
    reverse
    -0.60
    bows
    -0.59
    lee
    -0.59
    istan
    -0.59
    POSITIVE LOGITS
     important
    3.29
    important
    2.57
     Important
    2.29
     crucial
    2.20
     vital
    1.91
     valuable
    1.86
     essential
    1.83
    Important
    1.76
     interesting
    1.71
     invaluable
    1.66
    Activations Density 0.025%

    No Known Activations