© 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. 8-RES-JB
    11. 7719
    Prev
    Next
    INDEX
    Explanations

    mentions of fossils and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fossils and archaeological discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Synd
    -0.77
    ttle
    -0.73
    OPA
    -0.72
     blockers
    -0.71
     throttle
    -0.69
    Demand
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
    assion
    -0.68
     Rage
    -0.68
    controller
    -0.68
    POSITIVE LOGITS
     excav
    1.33
     archaeological
    1.33
     unearthed
    1.31
     excavation
    1.28
     archae
    1.25
     arte
    1.16
     Archae
    1.15
     archaeologists
    1.11
     specimens
    1.09
     fragments
    1.03
    Activations Density 0.172%

    No Known Activations