© 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. 11-RES-JB
    11. 7046
    Prev
    Next
    INDEX
    Explanations

    contexts related to archaeology and excavations

    oai_token-act-pair · gpt-3.5-turbo

    specifics related to archaeological findings and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ominated
    -0.83
    Fed
    -0.80
    EStreamFrame
    -0.80
     Comcast
    -0.80
     whipping
    -0.76
     Fedora
    -0.76
     throttle
    -0.75
     whine
    -0.75
     Zucker
    -0.74
     vaping
    -0.74
    POSITIVE LOGITS
     archaeologists
    2.27
     excav
    2.19
     excavation
    2.16
     archae
    2.13
     archaeological
    2.11
     Archae
    2.05
     unearthed
    1.60
     arche
    1.57
     Antiqu
    1.55
     burial
    1.44
    Activations Density 0.546%

    No Known Activations