INDEX

Explanations

phrases related to returning or repatriating to a specific location

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

 kasarigan

-0.60

awtextra

-0.56

AddRange

-0.55

 drag

-0.53

olastic

-0.51

żdy

-0.51

pides

-0.50

⤹

-0.49

overload

-0.49

chaun

-0.49

POSITIVE LOGITS

 originais

0.73

Portail

0.69

 indietro

0.68

 rejoined

0.67

返

0.66

に戻

0.65

回到

0.64

 döne

0.64

 reverting

0.63

回到了

0.63

Activations Density 0.174%

phrases related to returning or repatriating to a specific location

No Comments

No Known Activations