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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2006
    Prev
    Next
    INDEX
    Explanations

    references to secret societies, organizations, and conspiracy theories, such as Knights Templar, Illuminati, Freemasonry, and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to secret societies and organizations, particularly those associated with the Templars, Freemasonry, and the Illuminati

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geon
    -0.80
    blank
    -0.73
    rums
    -0.65
    cially
    -0.65
    caps
    -0.64
    aple
    -0.63
    ulf
    -0.61
    impact
    -0.60
    older
    -0.60
    facing
    -0.60
    POSITIVE LOGITS
     Templar
    0.99
     Templ
    0.88
     dues
    0.80
    uria
    0.78
    asonic
    0.77
     Brotherhood
    0.75
     Oath
    0.75
     Order
    0.75
     Lodge
    0.72
     creed
    0.71
    Activations Density 0.055%

    No Known Activations