INDEX

Explanations

references to the concept of "second" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 سكانية

-0.79

 Maho

-0.71

 Theſe

-0.70

 nød

-0.66

 CAFE

-0.63

 ſeveral

-0.62

loài

-0.62

 itſelf

-0.61

 Diſ

-0.60

fú

-0.59

POSITIVE LOGITS

 second

0.90

 SECOND

0.87

 Second

0.86

 ikinci

0.84

Second

0.82

第二

0.81

 השני

0.81

second

0.80

 segunda

0.76

Geplaatst

0.76

Activations Density 0.761%

references to the concept of "second" in various contexts

No Comments

No Known Activations