© 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. 16390
    Prev
    Next
    INDEX
    Explanations

    the word "pair" followed by another term in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "pair" in various contexts

    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
    ulhu
    -1.02
    Interstitial
    -0.76
    inez
    -0.71
    ICLE
    -0.69
    UGE
    -0.67
    pmwiki
    -0.67
    ancock
    -0.67
    avez
    -0.65
     Causes
    -0.63
    ugu
    -0.63
    POSITIVE LOGITS
    pair
    1.01
    rings
    0.96
     pair
    0.90
    ably
    0.89
    ings
    0.89
    wise
    0.82
    ring
    0.79
    lihood
    0.78
    pieces
    0.77
     halves
    0.76
    Activations Density 0.010%

    No Known Activations