© 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. 1-RES-JB
    11. 16397
    Prev
    Next
    INDEX
    Explanations

    instances of the word "waited"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "waited."

    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
    andals
    -0.71
    oral
    -0.67
    abol
    -0.66
    admin
    -0.65
    ciplinary
    -0.64
    adem
    -0.63
    Reviewer
    -0.62
    raction
    -0.62
    part
    -0.61
    obby
    -0.61
    POSITIVE LOGITS
     patiently
    1.32
     waited
    1.18
     waits
    1.09
     wait
    1.03
     waiting
    1.01
     anx
    0.95
     Waiting
    0.93
    wait
    0.91
     aloud
    0.85
     await
    0.84
    Activations Density 0.005%

    No Known Activations