© 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
    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. 7491
    Prev
    Next
    INDEX
    Explanations

    terms related to knots and blood clots

    oai_token-act-pair · gpt-3.5-turbo

    terms related to knots and entanglements

    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
    ONSORED
    -0.91
    nesota
    -0.87
    arthed
    -0.72
     indo
    -0.66
    ioch
    -0.65
    Asset
    -0.65
    BUS
    -0.64
    baugh
    -0.64
     Ames
    -0.62
    ×Ļ
    -0.62
    POSITIVE LOGITS
     knot
    1.12
     knots
    1.02
    weed
    1.00
    ty
    0.92
    ting
    0.91
    ishes
    0.89
    ties
    0.87
    istani
    0.83
    hered
    0.78
    urtles
    0.78
    Activations Density 0.013%

    No Known Activations