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. 1-RES-JB
    6. 19037
    Prev
    Next
    INDEX
    Explanations

    details or references related to specific studies or research projects

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports entities and the concept of summarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acters
    -0.97
    yss
    -0.91
    cffff
    -0.90
    ortium
    -0.90
    ndum
    -0.88
    manship
    -0.87
    mine
    -0.87
     Leilan
    -0.87
    inant
    -0.84
    bos
    -0.84
    POSITIVE LOGITS
     Antar
    0.76
     Procedures
    0.72
     Malik
    0.71
     Krug
    0.70
     Meal
    0.69
     gist
    0.66
     Gadget
    0.66
    ³
    0.66
     Hust
    0.65
    DERR
    0.64
    Activations Density 0.029%

    No Known Activations