Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20614
    Prev
    Next
    INDEX
    Explanations

    references to settlements or agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "settlement."

    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
     Flip
    -0.70
    MAG
    -0.70
    æĦ
    -0.68
    CSS
    -0.68
     Insp
    -0.66
     Instruct
    -0.65
    åĭ
    -0.65
    bec
    -0.64
     selector
    -0.62
    cd
    -0.62
    POSITIVE LOGITS
     settlement
    3.97
     Settlement
    3.16
     settlements
    3.11
    ettlement
    2.17
    sett
    1.93
     Sett
    1.91
     settlers
    1.70
     settling
    1.62
     settle
    1.57
     sett
    1.50
    Activations Density 0.020%

    No Known Activations