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. 6978
    Prev
    Next
    INDEX
    Explanations

    words related to wetness and moisture

    oai_token-act-pair · gpt-3.5-turbo

    references to water or wetness in various contexts

    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
    Angelo
    -0.92
     Vanguard
    -0.82
    Code
    -0.77
    ancer
    -0.71
    ancers
    -0.68
    abad
    -0.68
    agi
    -0.68
    arg
    -0.68
    anium
    -0.67
     Cohn
    -0.67
    POSITIVE LOGITS
     wet
    3.46
     Wet
    2.23
     dry
    1.88
     moist
    1.83
     damp
    1.61
     rainy
    1.59
     soaked
    1.51
     wetlands
    1.51
     moisture
    1.50
     drying
    1.49
    Activations Density 0.018%

    No Known Activations