Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22187
    Prev
    Next
    INDEX
    Explanations

    text related to advanced technology, including artificial intelligence, automation, autonomous systems, and futuristic concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to voice assistants and automation technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.82
    agall
    -0.80
     Chapter
    -0.80
    #$#$
    -0.75
    lishes
    -0.75
    iatus
    -0.74
    utory
    -0.70
     Sabb
    -0.69
     adjourn
    -0.68
    estones
    -0.68
    POSITIVE LOGITS
     wearable
    1.07
     sensors
    0.99
     bots
    0.97
     robotic
    0.93
     Kinect
    0.93
     OLED
    0.93
     automation
    0.93
     robots
    0.92
    earable
    0.91
     technology
    0.90
    Activations Density 0.633%

    No Known Activations