INDEX

Explanations

ratings and emotional reactions to experiences or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

RenderAtEndOf

-0.60

 linkovi

-0.52

 Pneum

-0.51

 Batter

-0.50

 TimeUnit

-0.50

 Roskov

-0.49

 DataAccess

-0.48

 Però

-0.48

Hyg

-0.47

 UITextField

-0.47

POSITIVE LOGITS

笑了笑

0.54

LikeLiked

0.53

[])

0.53

看着他

0.53

叹了口气

0.52

喊道

0.51

glio

0.50

笑道

0.49

 Sorensen

0.49

摇摇头

0.48

Activations Density 0.017%

ratings and emotional reactions to experiences or items

No Comments

No Known Activations