© 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. 4-RES-JB
    11. 7084
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparatives, specifically mentioning something as more than ever before

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a comparison to previous times or states of being

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

    No Comments

    Negative Logits
    okin
    -0.61
     Yar
    -0.60
     Tags
    -0.59
     Luck
    -0.59
     Zy
    -0.58
     Heisman
    -0.57
    char
    -0.57
    sym
    -0.57
     McA
    -0.57
    oute
    -0.57
    POSITIVE LOGITS
    theless
    1.09
    THING
    0.87
     EVER
    0.72
    entimes
    0.71
     dreamed
    0.71
     imagined
    0.69
     recorded
    0.67
     depended
    0.66
    eker
    0.66
     existed
    0.64
    Activations Density 0.014%

    No Known Activations