© 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. 6-RES-JB
    11. 19675
    Prev
    Next
    INDEX
    Explanations

    words related to archaeology and ancient remains

    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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PID
    -0.78
    OPA
    -0.78
    controller
    -0.75
    BuyableInstoreAndOnline
    -0.69
    channelAvailability
    -0.69
    PLAY
    -0.68
    Plug
    -0.67
     Maver
    -0.66
     Synd
    -0.66
    redo
    -0.64
    POSITIVE LOGITS
     excav
    1.22
     archaeological
    1.16
     unearthed
    1.10
     excavation
    1.10
     archae
    1.07
     arte
    1.05
     specimens
    1.04
     collections
    0.99
     Archae
    0.97
     archaeologists
    0.95
    Activations Density 0.125%

    No Known Activations