© 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. 8-RES-JB
    11. 17214
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms related to cooking and food, such as "Cooking" and "Chow."

    oai_token-act-pair · gpt-3.5-turbo

    references to cooking and recipe-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arsen
    -0.59
    ilater
    -0.58
    ufact
    -0.58
     lobb
    -0.56
    ĸļ
    -0.54
    soDeliveryDate
    -0.54
    ailable
    -0.51
    escription
    -0.51
     territ
    -0.51
     unpop
    -0.51
    POSITIVE LOGITS
     Meditation
    0.64
    uly
    0.61
    terness
    0.60
    nir
    0.59
    stic
    0.58
    Ħ¢
    0.58
    lich
    0.56
     Cooking
    0.56
    nova
    0.55
    tto
    0.55
    Activations Density 0.900%

    No Known Activations