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. 902
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal activities and official procedures, specifically the action of lodging appeals or petitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lodge" in various contexts, particularly in relation to lodging complaints or petitions

    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
    oppable
    -0.82
     spacing
    -0.78
    Buzz
    -0.75
     Cyborg
    -0.69
    Iraq
    -0.68
    ãĥ¼ãĤ¯
    -0.66
     flip
    -0.66
     Saiyan
    -0.66
     swaps
    -0.66
     automation
    -0.65
    POSITIVE LOGITS
     lodge
    3.49
     lodged
    3.06
     lod
    2.36
     Lodge
    2.29
     lodging
    2.25
     Lod
    1.92
     cabin
    1.09
     hut
    1.03
     Masonic
    0.97
     loft
    0.90
    Activations Density 0.031%

    No Known Activations