INDEX

Explanations

phrases indicating uncertainty or reservation in a statement

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

fta

-1.30

 secon

-1.29

 oner

-1.29

aen

-1.28

 emphat

-1.26

 „,

-1.26

 seiz

-1.26

 ?...

-1.21

hcm

-1.21

 perfon

-1.21

POSITIVE LOGITS

 digress

0.76

 also

0.67

 still

0.64

 também

0.62

 aren

0.59

isn

0.59

 wasn

0.59

don

0.58

 worse

0.57

 didn

0.57

Activations Density 0.397%

phrases indicating uncertainty or reservation in a statement

No Comments

No Known Activations