© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 9215
    Prev
    Next
    INDEX
    Explanations

    mentions of ancient civilizations, cultures, texts, and artifacts

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient civilizations and their characteristics

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

    No Comments

    Negative Logits
    imaru
    -0.91
    vous
    -0.88
    elight
    -0.88
    odder
    -0.86
    owitz
    -0.83
    kers
    -0.83
    channelAvailability
    -0.82
    avering
    -0.81
    TPPStreamerBot
    -0.78
    Demand
    -0.76
    POSITIVE LOGITS
     antiquity
    0.99
     Egyptian
    0.98
     burial
    0.97
     heritage
    0.95
     relic
    0.93
     relics
    0.92
     civilizations
    0.91
     civilisation
    0.91
     Greek
    0.90
     civilization
    0.86
    Activations Density 0.024%

    No Known Activations