© 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. 0-RES-JB
    11. 20231
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "do" followed by another verb

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alus
    -0.77
    Scotland
    -0.66
    ched
    -0.64
    abl
    -0.64
    eter
    -0.63
     Nou
    -0.60
     aggregation
    -0.59
    hemer
    -0.59
    hun
    -0.56
     semif
    -0.56
    POSITIVE LOGITS
     DO
    3.74
    DO
    2.03
     DON
    1.64
     DID
    1.54
     DOES
    1.39
     Do
    1.34
     ARE
    1.31
    do
    1.27
     NEVER
    1.24
     DEAD
    1.24
    Activations Density 0.015%

    No Known Activations