© 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. 10-RES-JB
    11. 19025
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or trends in data

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating observations or changes over time

    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
    Newsletter
    -0.84
    Truth
    -0.74
    SOURCE
    -0.70
    Mine
    -0.69
    trap
    -0.67
    ãĤ±
    -0.67
    alias
    -0.67
    heit
    -0.66
    bda
    -0.65
    ovie
    -0.65
    POSITIVE LOGITS
     firsthand
    1.12
     fewer
    0.94
     drastic
    0.94
    awed
    0.92
     improvements
    0.90
    dust
    0.89
     gradual
    0.87
     declines
    0.87
     dramatic
    0.84
     improvement
    0.84
    Activations Density 0.068%

    No Known Activations