INDEX

Explanations

expressions of gratitude

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

thank you and thanks

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

EDEFAULT

-0.47

RenderAtEndOf

-0.47

 intégrée

-0.45

 engagé

-0.45

Rö

-0.44

StructEnd

-0.44

 ویکی‌آمباردا

-0.44

 vectorielle

-0.44

YMS

-0.44

engager

-0.43

POSITIVE LOGITS

 arşivlendi

0.42

 excuse

0.40

 useAppContext

0.36

thx

0.36

よろしくお願いします

0.35

act

0.34

AuthService

0.34

luia

0.33

occasione

0.33

 thank

0.33

Activations Density 0.015%

expressions of gratitude

thank you and thanks

No Comments

No Known Activations