Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7205
    Prev
    Next
    INDEX
    Explanations

    words related to various types of pressure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pressure"

    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
    eming
    -0.71
    ithe
    -0.68
    ADE
    -0.68
    aux
    -0.66
    uble
    -0.66
    ades
    -0.66
    Doc
    -0.65
    herer
    -0.65
    amac
    -0.64
    ade
    -0.64
    POSITIVE LOGITS
     pressure
    3.85
     pressures
    2.95
    pressure
    2.94
     Pressure
    2.86
     pressured
    2.01
     pressuring
    1.90
     tension
    1.51
     PRESS
    1.34
     momentum
    1.33
     strain
    1.32
    Activations Density 0.028%

    No Known Activations