INDEX

Explanations

references to measurements, specifically quantities related to cups in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

tvguidetime

-0.88

 lenker

-0.85

 Reverso

-0.71

Бахар

-0.69

+:+

-0.68

giène

-0.64

szön

-0.62

imerick

-0.61

ainville

-0.61

ChildIndex

-0.61

POSITIVE LOGITS

 émotion

0.72

 Emotions

0.72

DoubleQuotes

0.70

 emotion

0.70

 Emotion

0.69

emotion

0.67

ViewFeatures

0.64

Snapshot

0.64

 snapshot

0.64

Emotion

0.64

Activations Density 0.059%

references to measurements, specifically quantities related to cups in recipes

No Comments

No Known Activations