INDEX

Explanations

phrases that express disbelief or skepticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Wikimedijinoj

-0.75

 itſelf

-0.73

 myſelf

-0.69

HostException

-0.67

 betweenstory

-0.64

存于互联网档案馆

-0.64

subsubsection

-0.64

respectively

-0.61

 Simultaneously

-0.60

 themſelves

-0.58

POSITIVE LOGITS

TagHelpers

0.66

দ্

0.63

 فال

0.59

 definitely

0.57

 fallait

0.55

ISupport

0.55

وارض

0.54

 transfieras

0.54

Tyl

0.53

 THAT

0.52

Activations Density 0.069%

phrases that express disbelief or skepticism

No Comments

No Known Activations

phrases that express disbelief or skepticism

No Comments

No Known Activations