© 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. 0-RES-JB
    11. 2086
    Prev
    Next
    INDEX
    Explanations

    words associated with change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "transform" and its variations

    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
     Lack
    -0.82
    epad
    -0.74
    Ping
    -0.73
     Berm
    -0.71
     advis
    -0.70
    forum
    -0.68
     Jury
    -0.68
     DUI
    -0.65
    ourn
    -0.64
    AGES
    -0.64
    POSITIVE LOGITS
     transform
    3.26
     transformed
    2.84
     transformation
    2.76
     transforming
    2.74
     transforms
    2.73
    transform
    2.53
     transformations
    2.45
     Transformation
    2.34
     Transform
    2.31
    Transform
    1.94
    Activations Density 0.037%

    No Known Activations