INDEX

Explanations

instances of the pronoun "I"

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

"I" followed by opinion/thought verbs

np_acts-logits-general · gemini-2.0-flash

opinion statements starting with "I"

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

 CreateTagHelper

-0.84

IntoConstraints

-0.81

rungsseite

-0.79

 AssemblyTitle

-0.79

 BIBSYS

-0.73

клопе

-0.68

 CiNii

-0.68

 TextInputType

-0.67

HasColumnType

-0.66

页面存档备份

-0.65

POSITIVE LOGITS

 honestly

0.73

 guess

0.68

 suppose

0.68

 hope

0.65

 think

0.64

 know

0.63

 dunno

0.62

 sure

0.62

 even

0.60

don

0.60

Activations Density 0.227%

instances of the pronoun "I"

"I" followed by opinion/thought verbs

opinion statements starting with "I"

No Comments

No Known Activations