INDEX

Explanations

elements related to movies and their components

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

󠁢

-0.61

nehm

-0.59

 explicitly

-0.58

effectively

-0.56

ditionally

-0.56

UTELY

-0.56

 تضيفلها

-0.55

 direta

-0.54

ORES

-0.52

的大小

-0.51

POSITIVE LOGITS

 indeed

0.80

 فريبيس

0.66

 overall

0.65

חס

0.64

 Indeed

0.64

overall

0.63

 Overall

0.62

Overall

0.61

 compared

0.60

Indeed

0.60

Activations Density 0.505%

elements related to movies and their components

No Comments

No Known Activations