INDEX

Explanations

references to emotions and reactions related to thoughts and actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ourselves

-0.71

we

-0.67

让我们

-0.66

讓我們

-0.59

 нами

-0.57

 yourselves

-0.56

 vimos

-0.55

weil

-0.55

we

-0.54

我们在

-0.54

POSITIVE LOGITS

 Slowly

0.85

 Glan

0.78

Slowly

0.70

“

0.69

 Carefully

0.69

 Sigh

0.65

 Maybe

0.65

 Surely

0.65

 Turning

0.64

 Something

0.64

Activations Density 0.113%

references to emotions and reactions related to thoughts and actions

No Comments

No Known Activations