© 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. 14891
    Prev
    Next
    INDEX
    Explanations

    terms related to remote-controlling and autonomous technology like unmanned aircraft, robotic devices, and automation systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remote-controlled and unmanned robotic technologies

    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
    abal
    -0.84
    =-=-
    -0.84
    neg
    -0.81
    src
    -0.79
     ABE
    -0.77
    emi
    -0.76
    vere
    -0.72
    cake
    -0.71
    bourg
    -0.70
    OIL
    -0.70
    POSITIVE LOGITS
     device
    0.94
     devices
    0.89
     computing
    0.89
     vehicle
    0.88
     robotic
    0.87
     versions
    0.86
     dart
    0.86
     handheld
    0.86
     locom
    0.85
     machines
    0.83
    Activations Density 0.157%

    No Known Activations