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. 329
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of fluidity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of fluidity

    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
     Bye
    -0.77
    anty
    -0.73
    Church
    -0.71
     Tours
    -0.69
     Hallow
    -0.67
    Ap
    -0.67
     Chandra
    -0.67
    Christmas
    -0.66
    raise
    -0.66
     Teach
    -0.66
    POSITIVE LOGITS
     fluid
    3.94
     fluids
    2.64
    flu
    1.85
     liquids
    1.34
     liquid
    1.31
     flux
    1.22
     lubric
    1.20
     electroly
    1.19
     visc
    1.18
     hydraulic
    1.15
    Activations Density 0.028%

    No Known Activations