INDEX

Explanations

phrases indicating categorization or classification within groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webElementXpaths

-0.73

toHaveBeenCalled

-0.72

 فريبيس

-0.70

ecutive

-0.68

хіво

-0.67

دانشنامهٔ

-0.64

клопе

-0.64

Efq

-0.64

 utilisons

-0.63

 Hano

-0.62

POSITIVE LOGITS

うち

0.57

 közül

0.55

のうち

0.51

rmtree

0.50

 davon

0.48

其中

0.47

の中には

0.47

 darunter

0.47

WindowConstants

0.47

 diantaranya

0.46

Activations Density 0.203%

phrases indicating categorization or classification within groups

No Comments

No Known Activations