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. 2-RES-JB
    6. 24450
    Prev
    Next
    INDEX
    Explanations

    words related to geographic locations, specifically focusing on the word "States"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "States."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AUT
    -0.71
    esters
    -0.68
    CAST
    -0.66
    Ĥİ
    -0.64
    gotten
    -0.64
    èª
    -0.62
    eger
    -0.61
    earance
    -0.60
    acterial
    -0.60
    ŃĶ
    -0.60
    POSITIVE LOGITS
     States
    1.09
    manship
    0.90
     Parties
    0.85
    States
    0.83
    wide
    0.83
    men
    0.78
    man
    0.75
    pring
    0.75
     Nations
    0.74
     Governments
    0.74
    Activations Density 0.005%

    No Known Activations