INDEX

Explanations

words related to corporate and governmental interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 المعيارى

-0.64

Hentet

-0.59

("="

-0.58

 convertView

-0.58

 chỗ

-0.58

ionView

-0.57

 disambiguazione

-0.56

 BorderRadius

-0.56

RetentionPolicy

-0.55

 useAppContext

-0.54

POSITIVE LOGITS

 previously

1.11

 recently

0.97

 earlier

0.94

 sebelumnya

0.93

previously

0.91

Earlier

0.85

 Earlier

0.84

 announced

0.84

 ранее

0.84

earlier

0.83

Activations Density 0.315%

words related to corporate and governmental interactions

No Comments

No Known Activations