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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 1981
    Prev
    Next
    INDEX
    Explanations

    words related to fossils and paleontology

    oai_token-act-pair · gpt-3.5-turbo

    references to fossils and their significance in paleontology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blockers
    -0.74
     preempt
    -0.73
     Synd
    -0.72
    License
    -0.72
    OPA
    -0.70
     Prevention
    -0.70
    Boost
    -0.70
    LOS
    -0.69
    cipled
    -0.68
    Demand
    -0.68
    POSITIVE LOGITS
     excav
    1.40
     archaeological
    1.30
     unearthed
    1.28
     fragments
    1.21
     archae
    1.21
     specimens
    1.21
     excavation
    1.21
     arte
    1.18
     archaeologists
    1.17
     fossils
    1.15
    Activations Density 0.240%

    No Known Activations