INDEX

Explanations

numerical values and related measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.65

Mar

-0.59

-0.54

三百

-0.53

Dal

-0.53

Bal

-0.52

 Balkon

-0.52

nd

-0.52

二百

-0.51

POSITIVE LOGITS

oa̍t

0.94

 تضيفلها

0.90

ExtendWith

0.85

 myſelf

0.85

yntaxException

0.84

исленность

0.81

 itſelf

0.80

 Meksi

0.78

 Teich

0.76

 avoient

0.76

Activations Density 0.470%

numerical values and related measurements

No Comments

No Known Activations