INDEX

Explanations

phrases that describe specific methodologies or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 picioare

-0.52

 rumbo

-0.50

containsKey

-0.48

 Asimismo

-0.47

inguém

-0.47

 houſe

-0.47

zkod

-0.47

 miseria

-0.47

 Decke

-0.46

 Variante

-0.46

POSITIVE LOGITS

LookAnd

0.75

assertj

0.71

ValueStyle

0.66

 يتيمه

0.64

nteral

0.62

 resultCode

0.61

存于互联网档案馆

0.60

 >=",

0.57

HostException

0.57

IGraphics

0.56

Activations Density 0.321%

phrases that describe specific methodologies or approaches

No Comments

No Known Activations