INDEX

Explanations

references to coffee-related terms and activities within a specific setting

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 accla

-0.97

 shenan

-0.93

 ridu

-0.91

 sappi

-0.90

 cushi

-0.88

 scopri

-0.88

 cammin

-0.88

 purtroppo

-0.87

 poichè

-0.86

 vogli

-0.86

POSITIVE LOGITS

 coffee

1.57

coffee

1.40

 Coffee

1.37

Coffee

1.29

 COFFEE

1.07

 coffees

1.05

FFEE

0.95

 cafe

0.91

咖啡

0.90

 caffeine

0.90

Activations Density 0.072%

references to coffee-related terms and activities within a specific setting

No Comments

No Known Activations