INDEX

Explanations

phrases indicating usage in various contexts or applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

BeginInit

-0.64

 JpaRepository

-0.63

 يتيمه

-0.62

ParallelGroup

-0.61

sizeCache

-0.61

LookAnd

-0.59

νό

-0.57

WebElementEntity

-0.57

SpringBootTest

-0.56

ISupport

-0.55

POSITIVE LOGITS

 used

1.15

 usage

1.12

use

1.09

 Used

1.09

Used

1.07

 Usage

1.02

 uses

1.00

Usage

0.97

Use

0.92

used

0.90

Activations Density 0.295%

phrases indicating usage in various contexts or applications

No Comments

No Known Activations