© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20694
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and technology, particularly mobile phones and computers

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and usage across various devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autions
    -0.79
    lied
    -0.70
    ablishment
    -0.69
    æĪ¦
    -0.68
    isse
    -0.68
    claim
    -0.67
     Breed
    -0.66
    äºĶ
    -0.66
    odies
    -0.66
    igrants
    -0.65
    POSITIVE LOGITS
     tablet
    1.63
     iPod
    1.57
     iPad
    1.57
     laptop
    1.54
     smartphone
    1.51
     iPads
    1.47
     tablets
    1.47
     laptops
    1.39
     smartphones
    1.39
     Kindle
    1.38
    Activations Density 0.271%

    No Known Activations