© 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. 6-RES-JB
    11. 17665
    Prev
    Next
    INDEX
    Explanations

    words related to actively seeking or searching for something

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "searching."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cision
    -0.76
    Production
    -0.71
    mos
    -0.66
    adra
    -0.64
    received
    -0.63
    earned
    -0.63
    assault
    -0.62
    death
    -0.62
    parable
    -0.62
    activation
    -0.62
    POSITIVE LOGITS
     frantically
    0.90
    emouth
    0.84
     diligently
    0.81
     unsuccessfully
    0.71
     blindly
    0.71
    ify
    0.70
    Ô
    0.70
     anx
    0.69
     unsolved
    0.67
     Tin
    0.67
    Activations Density 0.049%

    No Known Activations