INDEX

Explanations

the repeated use of the word "are" in various contexts

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

forms of 'to be'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

https

-0.50

 https

-0.48

jshint

-0.48

↵↵↵↵

-0.41

PosX

-0.38

test

-0.38

Pug

-0.38

onSubmit

-0.38

POSITIVE LOGITS

are

1.11

 estão

0.95

 blevet

0.85

 jsou

0.84

 were

0.82

 είναι

0.82

 são

0.82

 nejsou

0.82

 blitt

0.81

 jesteśmy

0.81

Activations Density 0.230%

the repeated use of the word "are" in various contexts

forms of 'to be'

No Comments

No Known Activations