© 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. 10-RES-JB
    11. 16539
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that continue a conversation or narration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continued" or variations of it that indicate ongoing actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.90
    errilla
    -0.77
    Frameworks
    -0.73
    ousands
    -0.73
    eros
    -0.71
    assium
    -0.67
    ocene
    -0.64
    istani
    -0.63
    ilibrium
    -0.63
    aughtered
    -0.61
    POSITIVE LOGITS
     asserting
    0.79
     stating
    0.78
    :"
    0.77
     explaining
    0.77
     emphasizing
    0.77
     omin
    0.77
     saying
    0.76
     sarcast
    0.75
     noting
    0.75
     insisting
    0.75
    Activations Density 0.028%

    No Known Activations