INDEX

Explanations

references to beverages, particularly coffee and tea

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

Types of drinks

np_acts-logits-general · gemini-2.0-flash

coffee, tea, and drinks

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

HtmlAttribute

-0.54

othelioma

-0.54

 uszkod

-0.51

 budowy

-0.49

 carnes

-0.48

 arşivlendi

-0.47

 responsabilità

-0.47

alleye

-0.46

AddTagHelper

-0.45

 dezelve

-0.45

POSITIVE LOGITS

 coffee

1.05

 drink

1.04

 drinks

1.01

 beverage

0.95

 caffeine

0.91

 espresso

0.90

 beverages

0.90

coffee

0.90

 Coffee

0.88

drink

0.88

Activations Density 0.138%

references to beverages, particularly coffee and tea

Types of drinks

coffee, tea, and drinks

No Comments

No Known Activations