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. 19696
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Storm."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Storm"

    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
    omed
    -0.73
     cylinders
    -0.72
     anat
    -0.71
    nas
    -0.68
    interstitial
    -0.68
     cylinder
    -0.67
    */(
    -0.66
     commer
    -0.66
     ub
    -0.65
     authent
    -0.64
    POSITIVE LOGITS
     Storm
    4.07
    Storm
    3.01
     storm
    2.05
    storm
    1.74
     storms
    1.61
     Tornado
    1.43
     Tempest
    1.37
     Thunder
    1.33
     Typhoon
    1.32
    Thunder
    1.25
    Activations Density 0.008%

    No Known Activations