INDEX

Explanations

actions related to manipulating or processing information efficiently

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

Followed by an infinitive or preposition

np_acts-logits-general · gemini-2.0-flash

verbs of action and purpose

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 saites

-0.54

 ngào

-0.52

сылкі

-0.49

hdysval

-0.48

SpringBootTest

-0.46

 journalistes

-0.43

Quest

-0.42

 langt

-0.41

esthesia

-0.41

 мной

-0.41

POSITIVE LOGITS

enumi

0.76

脚注の使い方

0.76

\{\\

0.74

انجليز

0.68

 ול

0.67

__":

0.66

Specifically

0.65

 المعيارى

0.64

первых

0.64

setObjectName

0.64

Activations Density 0.401%

actions related to manipulating or processing information efficiently

Followed by an infinitive or preposition

verbs of action and purpose

No Comments

No Known Activations