INDEX

Explanations

activities related to watching and listening to media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 mikrofon

-0.59

adə

-0.56

 pageContext

-0.56

 núcleo

-0.52

 мѣ

-0.51

 escribió

-0.51

 WRITING

-0.51

Географиясе

-0.50

rédients

-0.50

POSITIVE LOGITS

 movies

1.54

 movie

1.19

 films

1.14

movies

1.02

 Movies

0.99

 cartoons

0.97

 documentaries

0.93

Movies

0.89

 películas

0.89

TV

0.88

Activations Density 0.272%

activities related to watching and listening to media content

No Comments

No Known Activations