© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    sequences of words related to pairs or groupings

    oai_token-act-pair · gpt-3.5-turbo

    references to pairs, particularly in a biological or comparative context

    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
     agenda
    -0.71
    ernaut
    -0.67
     grasp
    -0.64
     cess
    -0.63
     setback
    -0.63
     mark
    -0.61
    gamer
    -0.61
    ock
    -0.59
    root
    -0.59
     stop
    -0.58
    POSITIVE LOGITS
     pairs
    3.87
     packs
    1.58
    pair
    1.28
     combinations
    1.26
     bundles
    1.23
    packs
    1.23
     layers
    1.22
     sets
    1.22
     Pair
    1.22
     couples
    1.20
    Activations Density 0.027%

    No Known Activations