© 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. 7-RES-JB
    11. 4369
    Prev
    Next
    INDEX
    Explanations

    archaeological terms and mentions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to archaeology and archaeologists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unconditional
    -0.81
    nir
    -0.72
    SB
    -0.69
     Unic
    -0.68
    rone
    -0.68
    lessness
    -0.68
     Senators
    -0.68
    BuyableInstoreAndOnline
    -0.67
    lessly
    -0.62
    channelAvailability
    -0.62
    POSITIVE LOGITS
     archae
    1.24
     excav
    1.20
     excavation
    1.09
     archaeological
    1.04
     archaeologists
    1.00
     Archae
    0.95
     digs
    0.88
    ifacts
    0.87
     arte
    0.87
     graves
    0.84
    Activations Density 0.031%

    No Known Activations