© 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. 1846
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons around the concept of "relative" or "relatively"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "relatively" to indicate comparisons

    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
    tein
    -0.81
    inis
    -0.80
     Polo
    -0.78
    arta
    -0.74
    ieu
    -0.73
    will
    -0.72
    rings
    -0.71
    PT
    -0.71
     Landing
    -0.71
    iens
    -0.70
    POSITIVE LOGITS
     unaffected
    1.01
     unchanged
    0.94
     innocuous
    0.91
     insignificant
    0.91
     insensitive
    0.90
     tame
    0.89
     scarce
    0.87
     benign
    0.86
     harmless
    0.85
     unpop
    0.84
    Activations Density 0.011%

    No Known Activations