© 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. 3512
    Prev
    Next
    INDEX
    Explanations

    words related to growth, development, and change

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating growth, change, or trends over time

    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
     Founding
    -0.77
    ij士
    -0.72
     upbringing
    -0.63
     parting
    -0.61
     Ended
    -0.59
     predec
    -0.59
    ilitarian
    -0.58
    cemic
    -0.57
    croft
    -0.56
    odan
    -0.55
    POSITIVE LOGITS
     lately
    1.07
     faster
    1.03
     rapidly
    1.03
     steadily
    0.98
     everywhere
    0.97
     increasingly
    0.91
     fast
    0.88
     Slowly
    0.88
     globally
    0.88
     slowly
    0.87
    Activations Density 0.600%

    No Known Activations