INDEX

Explanations

mentions of awards and winning achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

цина

-0.66

 band

-0.53

anglès

-0.52

Followers

-0.52

 stadio

-0.50

Toys

-0.50

 device

-0.49

CGRectMake

-0.48

 kohta

-0.48

Santis

-0.48

POSITIVE LOGITS

winning

1.94

 Winning

1.53

 winning

1.51

Winning

1.44

 bestselling

1.00

winner

0.90

winners

0.89

nominated

0.89

 winners

0.80

 winner

0.78

Activations Density 0.110%

mentions of awards and winning achievements

No Comments

No Known Activations