INDEX

Explanations

the word "in," indicating a focus on locations or contexts

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

"in" followed by a determiner or possessive

np_acts-logits-general · gemini-2.0-flash

in the

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

中には

-0.61

|}{$

-0.59

ostante

-0.56

isNameExpr

-0.50

&__

-0.49

manera

-0.48

neath

-0.48

 sorte

-0.48

 WaitForSeconds

-0.47

 hebdomada

-0.47

POSITIVE LOGITS

 ivelany

0.73

 action

0.64

 Wikimedijinoj

0.63

 Action

0.60

 steroids

0.60

!*\

0.59

NameInMap

0.59

AsUp

0.58

 Prisons

0.57

 nahilalakip

0.56

Activations Density 0.412%

the word "in," indicating a focus on locations or contexts

"in" followed by a determiner or possessive

in the

No Comments

No Known Activations