© 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. 0-RES-JB
    11. 8302
    Prev
    Next
    INDEX
    Explanations

    computer-related terms related to booting up or restarting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to booting or rebooting computer systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tsuk
    -0.76
     mercury
    -0.71
     merit
    -0.71
     withstand
    -0.69
     fiber
    -0.69
     outweigh
    -0.68
     prohib
    -0.67
     transm
    -0.67
     ang
    -0.66
     sen
    -0.66
    POSITIVE LOGITS
     Boot
    3.82
    Boot
    2.60
    boot
    1.94
     Reboot
    1.26
     boot
    1.26
     Boots
    1.25
     boots
    1.16
     Garage
    1.08
     Doodle
    1.06
     booted
    1.00
    Activations Density 0.025%

    No Known Activations