Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 1747
    Prev
    Next
    INDEX
    Explanations

    email and social media addresses with a .com domain

    oai_token-act-pair · gpt-3.5-turbo

    mentions of websites, particularly those ending with ".com"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     robbers
    -0.74
     masks
    -0.71
     Syri
    -0.66
     apes
    -0.65
     governors
    -0.64
     tradition
    -0.62
     Goldberg
    -0.62
     downs
    -0.62
     sed
    -0.62
     cosmetic
    -0.61
    POSITIVE LOGITS
    /?
    0.89
    Interstitial
    0.85
    urdue
    0.82
    nw
    0.80
    iott
    0.79
    hesion
    0.79
    ullivan
    0.76
    anse
    0.76
    biz
    0.75
    lishing
    0.75
    Activations Density 0.028%

    No Known Activations