INDEX

Explanations

keywords related to educational institutions and academic levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

MENAFN

-0.47

gefahr

-0.46

日閲覧

-0.43

-0.42

hamshire

-0.42

 Wirkung

-0.41

 riesgos

-0.41

effect

-0.41

gebung

-0.40

 célèbres

-0.40

POSITIVE LOGITS

OGND

0.99

 level

0.91

level

0.86

AsUp

0.84

 degree

0.81

TagMode

0.80

 students

0.80

 виправивши

0.79

 degrees

0.76

 ſch

0.74

Activations Density 0.295%

keywords related to educational institutions and academic levels

No Comments

No Known Activations