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. 7-RES-JB
    6. 3213
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "According to."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "According to" followed by attribution or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.79
    iphate
    -0.75
    gage
    -0.73
    ĸļ
    -0.70
    oided
    -0.67
    ograp
    -0.66
    obyl
    -0.65
    aired
    -0.65
     mathemat
    -0.65
     squared
    -0.65
    POSITIVE LOGITS
     sources
    0.94
     reports
    0.93
    reports
    0.88
     Folk
    0.88
     wik
    0.79
     legend
    0.77
     Wikipedia
    0.75
     insiders
    0.75
    Sources
    0.74
     rumors
    0.74
    Activations Density 0.064%

    No Known Activations