INDEX

Explanations

references to the abstract concept of 'it' in various contexts

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

"It" followed by a form of "to be."

np_acts-logits-general · gemini-2.0-flash

it followed by verb

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

diğ

-0.53

 besitzt

-0.52

 erhalten

-0.49

★★★★☆

-0.49

 possède

-0.48

 @"";

-0.48

 memiliki

-0.47

iliki

-0.46

Substituting

-0.46

 possess

-0.46

POSITIVE LOGITS

 виправивши

1.01

 '\\;'

0.99

RectangleBorder

0.97

 VIAF

0.97

 rained

0.92

 MainAxisSize

0.86

 مرئيه

0.83

AutoresizingMask

0.81

 ModelExpression

0.80

IntoConstraints

0.79

Activations Density 0.193%

references to the abstract concept of 'it' in various contexts

"It" followed by a form of "to be."

it followed by verb

No Comments

No Known Activations