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. 21224
    Prev
    Next
    INDEX
    Explanations

    words related to digital technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Digital."

    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
    beans
    -0.69
    è¦ļéĨĴ
    -0.68
     horm
    -0.67
    sever
    -0.66
     heal
    -0.62
    ulence
    -0.62
     sparing
    -0.62
    liners
    -0.62
     symp
    -0.62
    zbollah
    -0.62
    POSITIVE LOGITS
     Digital
    3.72
    Digital
    2.88
    digital
    2.42
     digital
    2.20
     digitally
    1.87
     Cyber
    1.57
     Electronic
    1.53
     Interactive
    1.42
     Virtual
    1.35
     Computer
    1.32
    Activations Density 0.011%

    No Known Activations