INDEX

Explanations

phrases that indicate conditions or qualifications, particularly focusing on the word "as."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ftate

-0.64

 preuves

-0.63

 stället

-0.62

 Chriftian

-0.62

 Libya

-0.60

 fubject

-0.60

 ſtate

-0.60

 Chrift

-0.60

Libya

-0.59

 vektör

-0.58

POSITIVE LOGITS

sowie

0.99

 other

0.94

mybatisplus

0.93

apimachinery

0.91

 unknownFields

0.88

PerformLayout

0.85

HasAnnotation

0.83

 וגם

0.83

NameInMap

0.83

 виправивши

0.81

Activations Density 0.087%

phrases that indicate conditions or qualifications, particularly focusing on the word "as."

No Comments

No Known Activations