INDEX

Explanations

phrases related to rankings and performance metrics in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

am

-0.55

Par

-0.55

 pares

-0.47

pou

-0.47

par

-0.45

Pa

-0.44

Am

-0.43

 lower

-0.43

 miss

-0.43

([]

-0.43

POSITIVE LOGITS

 isolado

0.77

OGND

0.77

 lenker

0.76

sizeCache

0.76

@"/

0.75

SharedDtor

0.75

 vainqueur

0.74

 Cæsar

0.74

 Administrativna

0.74

 ब्रेकडाउन

0.73

Activations Density 0.199%

phrases related to rankings and performance metrics in competitive contexts

No Comments

No Known Activations