© 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. 8-RES-JB
    11. 18665
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when."

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related context, particularly the usage of the word "when"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.75
    ictive
    -0.74
    aptic
    -0.68
    egu
    -0.68
    bear
    -0.66
    educ
    -0.64
    Die
    -0.64
    ateral
    -0.62
    ply
    -0.61
    icker
    -0.61
    POSITIVE LOGITS
    soever
    0.90
    fy
    0.70
     asked
    0.70
     transitioning
    0.69
     Prohibition
    0.69
     contacted
    0.68
     confronted
    0.68
    ornia
    0.68
     designing
    0.68
     viewed
    0.68
    Activations Density 0.106%

    No Known Activations