© 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. 3-RES-JB
    11. 12225
    Prev
    Next
    INDEX
    Explanations

    instances where something is physically unearthed or discovered

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dug" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kenn
    -0.78
    BuyableInstoreAndOnline
    -0.75
    Thomas
    -0.72
     Blueprint
    -0.72
    voice
    -0.69
     constitu
    -0.69
    Govern
    -0.69
     istg
    -0.68
    Case
    -0.67
    Andre
    -0.67
    POSITIVE LOGITS
     dug
    1.17
     dig
    1.13
     digging
    1.10
     digs
    1.08
     trenches
    0.98
    itial
    0.90
    isexual
    0.83
     excav
    0.83
     shaft
    0.82
     dred
    0.82
    Activations Density 0.012%

    No Known Activations