© 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. 3-RES-JB
    11. 433
    Prev
    Next
    INDEX
    Explanations

    words related to dynamic or changing elements

    oai_token-act-pair · gpt-3.5-turbo

    references to 'dynamic' concepts or elements within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chens
    -0.89
    ador
    -0.86
    chen
    -0.85
    zona
    -0.85
    hemat
    -0.85
    ñ
    -0.84
    furt
    -0.83
    creen
    -0.82
    OUGH
    -0.82
    mare
    -0.81
    POSITIVE LOGITS
     destro
    0.95
     Duo
    0.84
     duo
    0.82
     dynamic
    0.80
     upkeep
    0.77
     dynamically
    0.77
     enhancement
    0.77
     analy
    0.76
     streng
    0.76
     dynamics
    0.76
    Activations Density 0.006%

    No Known Activations