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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20636
    Prev
    Next
    INDEX
    Explanations

    phrases containing "both of" or "both of us"

    oai_token-act-pair · gpt-3.5-turbo

    references to pairs or groups of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.81
    assembly
    -0.77
    aukee
    -0.75
    ertodd
    -0.72
    ateurs
    -0.70
    pots
    -0.67
    lamm
    -0.66
    itual
    -0.66
    iameter
    -0.65
    eric
    -0.65
    POSITIVE LOGITS
     halves
    0.79
     sexes
    0.78
     administrations
    0.71
     Cups
    0.70
     Houses
    0.69
     parties
    0.68
     theirs
    0.67
     sides
    0.67
     thirds
    0.67
     these
    0.64
    Activations Density 0.038%

    No Known Activations