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. 3562
    Prev
    Next
    INDEX
    Explanations

    references to ancient civilizations or historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient civilizations and related concepts

    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
    vous
    -0.90
    imaru
    -0.86
    owitz
    -0.85
    avering
    -0.85
    odder
    -0.82
    channelAvailability
    -0.82
    elight
    -0.81
    yip
    -0.80
    bley
    -0.79
    kers
    -0.79
    POSITIVE LOGITS
     antiquity
    1.00
     relic
    0.99
     heritage
    0.98
     Egyptian
    0.95
     civilizations
    0.95
     relics
    0.94
     burial
    0.94
     Greek
    0.94
     civilization
    0.90
     civilisation
    0.90
    Activations Density 0.028%

    No Known Activations