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. 21331
    Prev
    Next
    INDEX
    Explanations

    references to the word "Rain"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Rain."

    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
    elong
    -0.75
    pc
    -0.75
    mc
    -0.72
     mach
    -0.69
    lib
    -0.67
     muscle
    -0.67
     masc
    -0.67
     pc
    -0.66
    aligned
    -0.66
     compe
    -0.65
    POSITIVE LOGITS
     Rain
    3.97
    Rain
    2.35
     rain
    1.77
     Rainbow
    1.32
     rains
    1.23
     Snow
    1.22
     Clouds
    1.16
     rainfall
    1.15
    rain
    1.15
     Sunny
    1.13
    Activations Density 0.012%

    No Known Activations