© 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. 1-RES-JB
    11. 14431
    Prev
    Next
    INDEX
    Explanations

    the word "is" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is" in various contexts

    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
    pse
    -0.74
    missible
    -0.69
    ject
    -0.65
     Loft
    -0.61
     Prof
    -0.60
     Principle
    -0.60
     craw
    -0.59
     Fact
    -0.59
     habit
    -0.58
     QC
    -0.58
    POSITIVE LOGITS
     mathemat
    0.80
    aucuses
    0.80
    ilogy
    0.80
    ADRA
    0.78
    icipated
    0.77
    olicited
    0.76
    displayText
    0.74
    aceutical
    0.70
    ifications
    0.70
    ileaks
    0.69
    Activations Density 0.000%

    No Known Activations