© 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. 0-RES-JB
    11. 7555
    Prev
    Next
    INDEX
    Explanations

    words related to algorithms or technical changes, possibly focusing on specific terms in different programming languages

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "trail."

    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
     calibration
    -0.73
     Pixel
    -0.68
     kindly
    -0.66
     Firm
    -0.65
     IU
    -0.65
     pencil
    -0.63
     Lauder
    -0.61
     calibrated
    -0.60
     proportion
    -0.59
     settings
    -0.59
    POSITIVE LOGITS
    tra
    4.56
    Tra
    2.42
    trap
    1.85
    trak
    1.60
     Tra
    1.52
    tro
    1.37
    tri
    1.33
    tr
    1.25
    tag
    1.24
    tre
    1.23
    Activations Density 0.012%

    No Known Activations