INDEX

Explanations

words and phrases related to quantity and frequency

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

every or each unit

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

 Appel

-0.44

 Geller

-0.40

SharedCtor

-0.40

 evil

-0.37

 Glanz

-0.37

 Alva

-0.36

 hence

-0.35

CodeAnalysis

-0.35

 possibility

-0.34

 Brandt

-0.34

POSITIVE LOGITS

每

1.72

每

1.48

 setiap

1.06

 tiap

1.06

Setiap

1.05

 Setiap

1.01

 mỗi

0.99

每个

0.99

每個

0.96

每次

0.95

Activations Density 0.002%

words and phrases related to quantity and frequency

every or each unit

No Comments

No Known Activations