© 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. 8-RES-JB
    11. 17738
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "that"

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.75
    zos
    -0.72
    stals
    -0.71
    ographed
    -0.70
    icons
    -0.70
    endants
    -0.68
    cycles
    -0.68
    oses
    -0.68
    pps
    -0.67
    boards
    -0.67
    POSITIVE LOGITS
     fateful
    1.20
     pesky
    1.17
     elusive
    0.96
     same
    0.92
    cher
    0.82
     equation
    0.81
     particular
    0.80
    same
    0.76
     aspect
    0.75
    chers
    0.74
    Activations Density 0.237%

    No Known Activations