INDEX

Explanations

phrases related to political interference and power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

+#+#

-0.82

InputBorder

-0.73

Życiorys

-0.66

tagHelperRunner

-0.63

WaitGroup

-0.63

UnsafeEnabled

-0.62

fromnode

-0.61

données

-0.60

 AssemblyCulture

-0.60

 MonoBehaviour

-0.60

POSITIVE LOGITS

are

0.58

 will

0.51

 were

0.49

 namely

0.48

 والذي

0.44

 into

0.43

रिक

0.43

 fanns

0.42

 Namely

0.41

bilecek

0.41

Activations Density 0.794%

phrases related to political interference and power dynamics

No Comments

No Known Activations