INDEX

Explanations

output statements related to arrays and structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 للاسماء

-0.71

期刊论文

-0.57

 intptr

-0.49

 kasarigan

-0.47

ValueStyle

-0.47

bruk

-0.45

Izvori

-0.43

 abrazo

-0.43

Atsauces

-0.43

 ciudadana

-0.43

POSITIVE LOGITS

 betweenstory

0.50

رشف

0.46

WireFormatLite

0.40

HandlerContext

0.39

 currentNode

0.38

 Chriftian

0.37

 seru

0.37

⟬

0.37

 HttpNotFound

0.36

bó

0.35

Activations Density 0.133%

output statements related to arrays and structures in code

No Comments

No Known Activations