INDEX

Explanations

instances of the word "use."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 gereken

-0.69

AFFIRMED

-0.63

 préféré

-0.61

 usato

-0.60

 auparavant

-0.59

 used

-0.59

 supuestamente

-0.59

 usados

-0.59

 formerly

-0.59

 vinto

-0.58

POSITIVE LOGITS

use

1.97

use

1.64

Use

1.49

Use

1.40

USE

1.16

uso

1.16

USE

1.06

ufe

1.02

 gebruik

0.97

protoimpl

0.96

Activations Density 0.219%

instances of the word "use."

No Comments

No Known Activations