INDEX

Explanations

references to Israel and its geopolitical context, particularly in relation to conflicts and diplomatic activities

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

Israel or Israeli topics

np_acts-logits-general · gemini-2.0-flash

Israel and Jewish contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.61

 Marten

-0.51

 Gonzaga

-0.48

typer

-0.47

liferay

-0.47

 lomb

-0.46

 Geister

-0.45

 مرئيه

-0.45

 Subpart

-0.45

Hun

-0.45

POSITIVE LOGITS

 Israel

1.95

 Israeli

1.85

Israel

1.75

Israeli

1.65

 ISRAEL

1.63

 Israelis

1.59

 Israël

1.52

 Jewish

1.51

 israel

1.48

 Isra

1.36

Activations Density 0.150%

references to Israel and its geopolitical context, particularly in relation to conflicts and diplomatic activities

Israel or Israeli topics

Israel and Jewish contexts

No Comments

No Known Activations