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. 3-RES-JB
    6. 14388
    Prev
    Next
    INDEX
    Explanations

    the term "mod" or variations of the word "modified"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "mod" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸
    -0.91
    âĸ¬
    -0.77
    ģĸ
    -0.75
    éĽ
    -0.74
    OHN
    -0.73
    âķIJâķIJ
    -0.71
     Unic
    -0.70
    ça
    -0.70
     Oaks
    -0.68
     Mata
    -0.68
    POSITIVE LOGITS
    ifications
    1.17
    ifiers
    1.15
    ding
    1.15
    ifiable
    1.15
    icum
    1.08
    elled
    1.06
    ifier
    1.05
    erate
    1.03
    ifying
    1.03
    esty
    1.02
    Activations Density 0.008%

    No Known Activations