INDEX

Explanations

numerical values and their formatting

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

 Nere

-0.67

Besch

-0.67

KELEY

-0.64

orianCalendar

-0.61

">:

-0.60

»։

-0.60

 Mala

-0.60

Lac

-0.56

 sqlSession

-0.56

 odkazy

-0.55

POSITIVE LOGITS

↵↵

0.66

":[{

0.56

 ismer

0.54

 нужда

0.51

mekte

0.51

''

0.50

oredCriteria

0.50

SpringBootTest

0.50

Tikang

0.50

 beginnetje

0.49

Activations Density 0.278%

numerical values and their formatting

No Comments

No Known Activations