© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3887
    Prev
    Next
    INDEX
    Explanations

    descriptions of food items and beverages

    oai_token-act-pair · gpt-3.5-turbo

    items related to food and beverages

    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
     firewall
    -0.80
     advers
    -0.76
     asset
    -0.75
     timelines
    -0.74
     Telecommunications
    -0.74
    onomous
    -0.73
     CIS
    -0.73
    criminal
    -0.71
    ajor
    -0.71
    Filename
    -0.70
    POSITIVE LOGITS
     meals
    1.32
     meal
    1.30
     snack
    1.30
     breakfast
    1.25
     snacks
    1.23
     tasting
    1.19
     salads
    1.18
     nutritious
    1.18
     beverages
    1.18
     sandwiches
    1.15
    Activations Density 0.904%

    No Known Activations