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. 9034
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a large size or amount

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "huge."

    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
     hereafter
    -0.80
     Procedure
    -0.71
    ®
    -0.71
    §
    -0.69
     Practices
    -0.67
     herein
    -0.67
    âĦ¢:
    -0.66
     advises
    -0.65
    idity
    -0.65
    âĦ¢
    -0.65
    POSITIVE LOGITS
     huge
    3.07
     HUGE
    2.64
    huge
    2.56
     massive
    2.39
     enormous
    2.35
     gigantic
    2.28
     colossal
    2.06
     big
    1.99
     Huge
    1.98
     immense
    1.97
    Activations Density 0.025%

    No Known Activations