Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12512
    Prev
    Next
    INDEX
    Explanations

    nutrition information in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    details related to cooking measurements and nutritional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibur
    -0.64
     CT
    -0.62
     scans
    -0.62
    FTWARE
    -0.61
     scanner
    -0.58
     fuzz
    -0.58
     Hz
    -0.57
     revoked
    -0.57
     belonging
    -0.57
    dq
    -0.56
    POSITIVE LOGITS
    Recipe
    1.19
    Ingredients
    1.16
     Recipe
    1.15
    isine
    1.02
     Ingredients
    1.01
     Instructions
    1.01
    cakes
    0.96
    Optional
    0.94
     Nutrition
    0.94
    ritional
    0.93
    Activations Density 0.128%

    No Known Activations