© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "was."

    oai_token-act-pair · gpt-3.5-turbo

    the word "was" indicating past tense

    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
    selves
    -0.55
    %%%%
    -0.54
    uits
    -0.54
    pport
    -0.52
    Merit
    -0.51
    ichever
    -0.50
    icial
    -0.49
    pread
    -0.49
     yourselves
    -0.48
    ogh
    -0.48
    POSITIVE LOGITS
     was
    2.56
    was
    2.10
     wasn
    2.10
     Was
    1.65
    Was
    1.61
     became
    1.56
     WAS
    1.54
     went
    1.50
     had
    1.48
     appeared
    1.46
    Activations Density 0.454%

    No Known Activations