© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for something

    oai_token-act-pair · gpt-3.5-turbo

    the act of searching or seeking

    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
    cision
    -0.84
    board
    -0.77
    cigarette
    -0.71
    mos
    -0.71
    death
    -0.70
    payment
    -0.66
    notice
    -0.65
    interstitial
    -0.65
    Downloadha
    -0.65
    ption
    -0.64
    POSITIVE LOGITS
     frantically
    0.83
    emouth
    0.80
     searches
    0.78
     queries
    0.75
     searching
    0.72
    ãĤ¦ãĤ¹
    0.71
     Eag
    0.70
     anx
    0.69
    âĸ¬
    0.69
     searched
    0.68
    Activations Density 0.026%

    No Known Activations