INDEX

Explanations

phrases indicating actions or assertions made by a group or collective subject

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

pronouns followed by verbs

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

EDEFAULT

-0.91

 '\\;'

-0.90

脚注の使い方

-0.87

AddTagHelper

-0.85

EndGlobalSection

-0.82

WebVitals

-0.81

 незавершена

-0.80

Бележки

-0.79

 تضيفلها

-0.76

Gambas

-0.75

POSITIVE LOGITS

 They

0.60

he

0.59

 saying

0.54

They

0.54

 they

0.53

He

0.53

 said

0.51

She

0.51

He

0.50

he

0.49

Activations Density 0.251%

phrases indicating actions or assertions made by a group or collective subject

pronouns followed by verbs

No Comments

No Known Activations