© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1275
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and automation, particularly focusing on voice assistants, autonomous systems, and artificial intelligence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and automation, particularly focusing on voice assistants and autonomous systems

    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
    iatus
    -0.86
    pite
    -0.86
     Chapter
    -0.76
    estones
    -0.73
    quart
    -0.71
    qs
    -0.70
     adjourn
    -0.70
    Catholic
    -0.69
    agall
    -0.67
    #$#$
    -0.67
    POSITIVE LOGITS
     wearable
    0.96
     robots
    0.96
     bots
    0.95
     sensors
    0.95
     technology
    0.94
     Bots
    0.89
     robotic
    0.88
     headsets
    0.88
    animate
    0.88
     Kinect
    0.87
    Activations Density 0.501%

    No Known Activations