© 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. 4-RES-JB
    11. 20564
    Prev
    Next
    INDEX
    Explanations

    the phrase "last but not least" in texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize comparisons or the concept of "at least."

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

    No Comments

    Negative Logits
    ijn
    -0.73
     Meadows
    -0.72
    uns
    -0.70
    per
    -0.70
    andem
    -0.67
    Avg
    -0.67
    umn
    -0.67
    utic
    -0.66
    angan
    -0.65
    thur
    -0.65
    POSITIVE LOGITS
     Ù
    0.78
     prominently
    0.77
     suffice
    0.75
     âĢº
    0.72
    LESS
    0.65
     squares
    0.65
     flattering
    0.64
    !--
    0.64
     Cyr
    0.62
     bolst
    0.62
    Activations Density 0.011%

    No Known Activations