© 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 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. 13019
    Prev
    Next
    INDEX
    Explanations

    phrases that typically start with "Usually"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Usually" and similar phrases indicating frequency or patterns of occurrence

    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
     continued
    -0.77
     embrace
    -0.73
     voice
    -0.71
     embracing
    -0.71
     voices
    -0.70
     hurt
    -0.69
     continuing
    -0.68
     failed
    -0.67
     regrets
    -0.67
     revolution
    -0.67
    POSITIVE LOGITS
    Usually
    2.72
     Usually
    2.65
     Typically
    2.60
    Typically
    2.39
     Normally
    2.24
    Normally
    2.19
    Generally
    2.01
    Often
    1.94
    usually
    1.94
     Generally
    1.89
    Activations Density 0.025%

    No Known Activations