© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18484
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or the act of comparing different things

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparison or evaluating differences

    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
    oÄŁ
    -0.79
    ther
    -0.68
    dar
    -0.67
     havoc
    -0.66
    gren
    -0.66
    jong
    -0.65
    ULE
    -0.65
    eland
    -0.65
    ktop
    -0.65
    starter
    -0.64
    POSITIVE LOGITS
     apples
    1.27
     favorably
    1.18
     comparing
    0.87
     favour
    0.84
     between
    0.82
    isons
    0.77
     comparisons
    0.77
     notes
    0.75
     compare
    0.74
     Compare
    0.74
    Activations Density 0.046%

    No Known Activations