© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1437
    Prev
    Next
    INDEX
    Explanations

    text related to the name "Rob"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Rob" in the context of robotics

    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
     thirst
    -0.76
     cumulative
    -0.75
     Gau
    -0.73
     Ven
    -0.72
     mercury
    -0.70
     plaque
    -0.70
     palate
    -0.69
     arteries
    -0.68
    ð
    -0.68
     pur
    -0.68
    POSITIVE LOGITS
    Rob
    3.68
    rob
    1.97
     Robotics
    1.94
     Robot
    1.83
     Robinson
    1.75
     Robots
    1.74
     Robo
    1.72
     ROB
    1.68
     Rob
    1.57
     robotics
    1.49
    Activations Density 0.014%

    No Known Activations