INDEX

Explanations

phrases indicating examples or exemplification

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

ereg

-0.60

Configurer

-0.58

XMLSchema

-0.54

IConfiguration

-0.53

ziná

-0.53

 Decoder

-0.52

 Amadeus

-0.52

 Constantine

-0.52

QApplication

-0.52

łgor

-0.51

POSITIVE LOGITS

 examples

1.33

 example

1.18

examples

1.16

 Beispiele

1.12

 Examples

1.09

Examples

1.07

 esempi

1.06

 eksemp

1.05

 exemples

1.04

 EXAMPLE

1.03

Activations Density 0.178%

phrases indicating examples or exemplification

No Comments

No Known Activations