INDEX

Explanations

code annotations and configuration details related to API services

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

 mergeFrom

-0.78

原始内容存档于

-0.72

AccessFile

-0.71

 tartalomajánló

-0.63

RegressionTest

-0.63

ooga

-0.62

鰭

-0.62

曖昧さ回避

-0.61

 Kamb

-0.61

ientôt

-0.60

POSITIVE LOGITS

RequestMapping

0.67

 AssemblyTitle

0.57

 ResponseEntity

0.52

 strade

0.43

GetMapping

0.42

 alimentaires

0.42

 hObject

0.42

 extérieurs

0.42

 émissions

0.41

 paille

0.40

Activations Density 0.052%

code annotations and configuration details related to API services

No Comments

No Known Activations