INDEX

Explanations

code-related structures and syntax, such as cases and property definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

rungsseite

-1.08

TagMode

-1.04

 متعلقه

-1.01

 ujednoznacz

-0.98

 Савезне

-0.98

Espèce

-0.97

 виправивши

-0.95

 tartalomajánló

-0.89

Rhestr

-0.89

OGND

-0.87

POSITIVE LOGITS

 jotka

0.44

0.43

etc

0.43

 Außerdem

0.41

etc

0.39

 همچنین

0.39

The

0.38

 että

0.38

and

0.38

 valamint

0.38

Activations Density 0.271%

code-related structures and syntax, such as cases and property definitions

No Comments

No Known Activations