© 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. 6-RES-JB
    11. 14730
    Prev
    Next
    INDEX
    Explanations

    references to specific Intel Core processors

    oai_token-act-pair · gpt-3.5-turbo

    references to computer processors, specifically Intel Core CPUs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.76
    IGHTS
    -0.76
    ought
    -0.74
    pload
    -0.71
    ospital
    -0.69
    dp
    -0.68
     captcha
    -0.68
    pez
    -0.68
    ights
    -0.68
     sidel
    -0.68
    POSITIVE LOGITS
    opsis
    0.86
    xit
    0.84
    lli
    0.77
     Core
    0.77
    rient
    0.75
    erity
    0.75
    lington
    0.74
    craft
    0.73
     Divinity
    0.72
    utils
    0.69
    Activations Density 0.020%

    No Known Activations