© 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. 4-RES-JB
    11. 10115
    Prev
    Next
    INDEX
    Explanations

    phrases related to dietary requirements and nutritional needs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dietary and nutritional factors

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

    No Comments

    Negative Logits
    hift
    -0.85
    ships
    -0.77
    oning
    -0.76
    etter
    -0.74
     Kinnikuman
    -0.72
    aday
    -0.71
    uber
    -0.71
     Rowe
    -0.69
    aunder
    -0.68
     Operator
    -0.67
    POSITIVE LOGITS
     supplements
    0.97
     habits
    0.95
    ritional
    0.93
     intake
    0.91
     cholesterol
    0.91
     dietary
    0.91
     diet
    0.90
     diets
    0.89
     carbohyd
    0.87
     fats
    0.85
    Activations Density 0.006%

    No Known Activations