INDEX

Explanations

statements emphasizing capabilities and individual achievements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

といって

-0.48

 Мексичка

-0.47

ništ

-0.46

 كومونز

-0.44

ant

-0.44

lső

-0.42

 corresponding

-0.41

EndContext

-0.41

 muualla

-0.41

клопе

-0.40

POSITIVE LOGITS

 ujednoznacz

1.01

ValueGeneration

0.66

RefNanny

0.63

tvguidetime

0.62

 Complexes

0.60

ellemző

0.56

 aidant

0.55

 éte

0.55

 absolue

0.55

 SEDS

0.55

Activations Density 0.360%

statements emphasizing capabilities and individual achievements

No Comments

No Known Activations