© 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. 17151
    Prev
    Next
    INDEX
    Explanations

    terms related to robotics and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to robotics and robotic technology

    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
    WAYS
    -0.79
    emi
    -0.77
    rees
    -0.70
    dn
    -0.70
    UGE
    -0.69
    ++++++++++++++++
    -0.68
     Fargo
    -0.66
    clair
    -0.66
    iyah
    -0.66
    uating
    -0.66
    POSITIVE LOGITS
     gri
    0.85
     robotic
    0.84
     robotics
    0.80
    ically
    0.77
     arm
    0.76
    ¥ŀ
    0.75
     robot
    0.75
     robots
    0.73
     prost
    0.71
     dinosaurs
    0.71
    Activations Density 0.013%

    No Known Activations