© 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. 3-RES-JB
    11. 9639
    Prev
    Next
    INDEX
    Explanations

    words related to carbohydrates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to carbohydrates and their impact on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.85
    DragonMagazine
    -0.83
    66666666
    -0.74
    Reviewer
    -0.72
    éĹ
    -0.69
    doms
    -0.68
    UAL
    -0.66
    é¾įå
    -0.66
    Ò
    -0.66
    liness
    -0.65
    POSITIVE LOGITS
    ohydrate
    1.28
    uncle
    1.05
     carb
    1.00
    ohyd
    0.93
    olina
    0.88
    amate
    0.88
    carb
    0.82
    odic
    0.80
    odies
    0.80
    ursed
    0.80
    Activations Density 0.012%

    No Known Activations