INDEX

Explanations

categories or classifications related to media, particularly television and film series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ChildScrollView

-0.73

 Egli

-0.65

הערות

-0.65

 oprot

-0.65

wpdb

-0.63

 '\\;'

-0.63

Билгалдахарш

-0.63

 correctes

-0.62

 acoper

-0.61

قایناق‌لار

-0.61

POSITIVE LOGITS

 صوتيه

0.61

 ComVisible

0.52

res

0.50

 IBOutlet

0.48

protoimpl

0.48

IsMutable

0.47

usza

0.46

 desti

0.45

vide

0.45

Portale

0.44

Activations Density 0.065%

categories or classifications related to media, particularly television and film series

No Comments

No Known Activations