© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sometimes" and its variations, indicating a focus on conditional or iterative situations

    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
    now
    -0.84
     presently
    -0.83
    currently
    -0.83
     ASAP
    -0.79
    today
    -0.76
     hereafter
    -0.76
     currently
    -0.74
     Currently
    -0.73
     now
    -0.72
     Now
    -0.71
    POSITIVE LOGITS
     accidentally
    0.98
     unintentionally
    0.95
     inadvertently
    0.95
     mistaken
    0.92
     downright
    0.91
     surprises
    0.87
     simply
    0.86
     stumble
    0.85
     inadvert
    0.85
     slip
    0.84
    Activations Density 0.337%

    No Known Activations