INDEX

Explanations

phrases indicating potential outcomes or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

しくて

-0.54

ﾟ

-0.48

cemic

-0.42

 biome

-0.42

']}

-0.42

pierw

-0.41

")[

-0.41

API

-0.40

anyahu

-0.40

>*/

-0.40

POSITIVE LOGITS

 متعلقه

0.78

 كومونز

0.78

 дописавши

0.78

AndEndTag

0.75

FUTURE

0.74

 <<<<<<<<<<<<<<

0.71

 propOrder

0.70

future

0.70

 future

0.69

脚注の使い方

0.69

Activations Density 0.571%

phrases indicating potential outcomes or conditions

No Comments

No Known Activations