© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3442
    Prev
    Next
    INDEX
    Explanations

    the word "right" used in a context indicating a particular point in time or decision

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "right now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raved
    -0.67
    âĢ¢
    -0.62
    jury
    -0.61
     Chic
    -0.59
    arts
    -0.57
    EEK
    -0.56
    âĹı
    -0.56
    resses
    -0.55
    arette
    -0.55
    advert
    -0.53
    POSITIVE LOGITS
     away
    1.13
     now
    1.05
    eous
    0.97
    away
    0.94
    now
    0.89
     NOW
    0.88
     Away
    0.81
     smack
    0.77
    arrow
    0.75
    Cooldown
    0.73
    Activations Density 0.040%

    No Known Activations