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

    Neuronpedia

    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. 1-RES-JB
    11. 10452
    Prev
    Next
    INDEX
    Explanations

    words related to archaeological excavations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to archaeological excavations and discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lass
    -0.80
     Hubbard
    -0.68
    states
    -0.65
    govern
    -0.65
    ---------
    -0.63
    state
    -0.63
    eworld
    -0.62
    names
    -0.62
     Missile
    -0.62
    stood
    -0.62
    POSITIVE LOGITS
     excav
    1.42
     excavation
    1.28
     digs
    0.94
     archaeological
    0.86
     digging
    0.83
     unearthed
    0.81
     dug
    0.80
     dred
    0.80
    ifacts
    0.79
    atform
    0.79
    Activations Density 0.016%

    No Known Activations