© 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. 7-RES-JB
    11. 23738
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and eating unhealthy foods

    oai_token-act-pair · gpt-3.5-turbo

    references to unhealthy eating habits or specific unhealthy foods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -1.01
    Operation
    -0.80
    soDeliveryDate
    -0.79
    yrinth
    -0.78
    CLASS
    -0.74
    projects
    -0.73
    Technical
    -0.72
    ciation
    -0.70
    foreseen
    -0.67
    Offic
    -0.67
    POSITIVE LOGITS
     grapes
    1.12
     berries
    1.10
     scraps
    0.97
     grape
    0.96
     cabbage
    0.93
     strawberries
    0.91
     contaminated
    0.90
     crap
    0.90
     juice
    0.89
     meals
    0.89
    Activations Density 0.220%

    No Known Activations