© 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. 553
    Prev
    Next
    INDEX
    Explanations

    words related to polymers

    oai_token-act-pair · gpt-3.5-turbo

    references to polymers, especially plastics

    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
    æ©
    -0.79
     Club
    -0.79
     Burnett
    -0.72
     Cheong
    -0.71
     Broncos
    -0.71
     Lauder
    -0.69
     Bauer
    -0.68
     Administration
    -0.67
     Rousse
    -0.67
     Titanic
    -0.67
    POSITIVE LOGITS
    gon
    1.28
    cycl
    1.06
    ester
    1.05
    meric
    1.04
    sty
    1.02
    phony
    1.00
    cil
    0.99
    chrome
    0.96
    atomic
    0.96
    acet
    0.94
    Activations Density 0.008%

    No Known Activations