INDEX

Explanations

forms of the verb "be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 itſelf

-0.82

 Jefus

-0.80

 pleaſure

-0.79

 triom

-0.75

 ſtate

-0.74

 houſe

-0.73

 Chriftian

-0.71

 purpoſe

-0.69

 ſeveral

-0.68

 iſt

-0.68

POSITIVE LOGITS

be

1.35

Be

1.21

Be

1.14

ToBe

1.02

 shouldBe

1.01

BE

1.00

 être

1.00

be

0.94

 able

0.91

 бъдат

0.90

Activations Density 0.217%

forms of the verb "be."

No Comments

No Known Activations