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. 3658
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms related to a political figure named Amarinder Singh

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals or characters, particularly those ending in "inder."

    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
     SPL
    -0.70
     oy
    -0.67
     Pirates
    -0.66
     unsc
    -0.65
     rapt
    -0.64
     indisc
    -0.62
     sac
    -0.62
     bil
    -0.62
     caps
    -0.62
     billions
    -0.61
    POSITIVE LOGITS
    inder
    4.79
    inders
    3.24
    inding
    1.94
    IND
    1.50
    ender
    1.20
    ind
    1.20
    endra
    1.10
    atson
    1.04
    utor
    1.03
    ander
    1.02
    Activations Density 0.005%

    No Known Activations