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. 10-RES-JB
    6. 20139
    Prev
    Next
    INDEX
    Explanations

    articles and opinion pieces with the term "op-ed"

    oai_token-act-pair · gpt-3.5-turbo

    references to opinion pieces and articles in newspapers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     levers
    -0.72
    ARA
    -0.71
    Plex
    -0.67
     weddings
    -0.66
    effic
    -0.64
     cleaners
    -0.62
     controls
    -0.61
     embryos
    -0.59
     Rescue
    -0.58
     transporter
    -0.57
    POSITIVE LOGITS
     titled
    1.30
     essay
    1.13
     penned
    1.11
     headlined
    1.11
     published
    1.09
     entitled
    1.07
     criticizing
    1.03
     reprinted
    1.00
     column
    0.97
    itled
    0.96
    Activations Density 0.119%

    No Known Activations