INDEX

Explanations

elements related to authority or hierarchical structures

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

 verschil

-0.57

干嘛

-0.56

创建时间

-0.54

什么呢

-0.54

manda

-0.53

 '\\;'

-0.53

 behulp

-0.53

圖片來源

-0.52

istoitu

-0.52

><?

-0.51

POSITIVE LOGITS

########.

0.91

__*/

0.84

 isNameExpr

0.70

welli

0.66

MSR

0.64

 MainAxisSize

0.64

'@/

0.63

0.62

 Mong

0.62

 iVar

0.61

Activations Density 0.101%

elements related to authority or hierarchical structures

No Comments

No Known Activations