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. 2-RES-JB
    6. 16683
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "opposites."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atche
    -0.82
    aven
    -0.78
    urrent
    -0.73
    ULT
    -0.73
    lished
    -0.71
    uay
    -0.71
    ule
    -0.70
    ashington
    -0.69
    Query
    -0.68
    brance
    -0.68
    POSITIVE LOGITS
     opposite
    0.97
    osite
    0.95
     sides
    0.85
     oppos
    0.82
     twins
    0.79
    lihood
    0.75
     twin
    0.75
     minded
    0.71
     halves
    0.71
     side
    0.70
    Activations Density 0.009%

    No Known Activations