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. 3-RES-JB
    6. 2490
    Prev
    Next
    INDEX
    Explanations

    questions asking for opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    repeated inquiries about opinions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clad
    -0.76
    conservancy
    -0.74
    ague
    -0.72
     clad
    -0.71
    recorded
    -0.64
    feeding
    -0.63
     Adin
    -0.62
    ipher
    -0.62
    Shipping
    -0.62
    yna
    -0.60
    POSITIVE LOGITS
    IUM
    0.74
     provoking
    0.68
     aloud
    0.67
    pad
    0.67
    ij士
    0.66
    agram
    0.65
     Polk
    0.64
     about
    0.64
    orial
    0.64
    olesterol
    0.63
    Activations Density 0.065%

    No Known Activations