INDEX

Explanations

specific nouns and terms related to activities and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 kasarigan

-0.64

Geplaatst

-0.58

󠁴

-0.53

 للاسماء

-0.48

 surla

-0.47

 Савезне

-0.45

ThemeOverlay

-0.43

 الرياضيه

-0.43

*);

-0.43

wapV

-0.42

POSITIVE LOGITS

們

1.19

们

1.16

sthe

1.00

们的

0.88

‌ها

0.86

es

0.83

ss

0.83

들은

0.81

́s

0.81

ssss

0.77

Activations Density 3.097%

specific nouns and terms related to activities and interactions

No Comments

No Known Activations