© 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. 0-RES-JB
    11. 5381
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Consider" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "consider" is used, indicating recommendations or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     missing
    -0.65
     sparking
    -0.64
     originals
    -0.63
     ribbon
    -0.62
     jack
    -0.61
     winner
    -0.60
     clicks
    -0.59
     coast
    -0.59
     continuously
    -0.59
     led
    -0.58
    POSITIVE LOGITS
     Consider
    3.49
    Consider
    3.19
    consider
    1.84
     Suppose
    1.80
     consider
    1.55
    Imagine
    1.34
     considerations
    1.33
     Recall
    1.27
    Think
    1.26
     Imagine
    1.23
    Activations Density 0.011%

    No Known Activations