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. 105
    Prev
    Next
    INDEX
    Explanations

    comparisons being made between different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "compare" in various contexts

    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
    mission
    -0.66
     Enhancement
    -0.64
    aria
    -0.64
    llers
    -0.62
     intact
    -0.61
    iday
    -0.59
    strom
    -0.58
     Panc
    -0.58
     clearance
    -0.56
    ent
    -0.56
    POSITIVE LOGITS
     compare
    3.75
     Compare
    2.56
     compares
    2.47
    Compare
    2.27
     comparison
    2.02
     comparing
    1.97
     comparisons
    1.84
     compared
    1.65
     equate
    1.61
     Comparison
    1.50
    Activations Density 0.018%

    No Known Activations