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. 10-RES-JB
    6. 15203
    Prev
    Next
    INDEX
    Explanations

    comparisons involving the term "other"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing the uniqueness or dominance of a subject relative to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isters
    -0.84
    ordes
    -0.78
    gets
    -0.73
    ãĥ¼ãĤ¯
    -0.72
    ernels
    -0.71
    undreds
    -0.69
    ometimes
    -0.69
    ften
    -0.68
    staking
    -0.67
    bows
    -0.67
    POSITIVE LOGITS
    worldly
    1.71
     conceivable
    1.19
     aspect
    1.17
    iator
    1.14
     circumstance
    1.07
     imaginable
    1.06
     avenue
    1.01
     kind
    1.00
     entity
    0.98
     option
    0.95
    Activations Density 0.037%

    No Known Activations