INDEX

Explanations

sentences expressing complexity and detail in opinions or analyses

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

highlights reasons

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

expandindo

-0.47

rrggbb

-0.47

SharedCtor

-0.46

 Administrativna

-0.46

 Chwiliwch

-0.44

 Numerade

-0.44

 мәкал

-0.42

 متعلقه

-0.41

IANGLES

-0.40

tagext

-0.39

POSITIVE LOGITS

 strangest

0.46

 deliberate

0.43

lső

0.42

 Teil

0.41

 ویکی‌پدیا

0.41

 sandalias

0.40

stdafx

0.40

contaminated

0.39

 Kato

0.38

 تانيه

0.38

Activations Density 0.205%

sentences expressing complexity and detail in opinions or analyses

highlights reasons

No Comments

No Known Activations