INDEX

Explanations

references to Jewish people and related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

bungs

-0.62

ография

-0.56

 سرد

-0.55

 Zhan

-0.55

kat

-0.55

 exécut

-0.54

Obt

-0.53

 duong

-0.53

 parson

-0.53

VSC

-0.53

POSITIVE LOGITS

 Israel

1.39

 Jews

1.33

 Jewish

1.33

Israel

1.26

 Israeli

1.22

 ISRAEL

1.21

 Israël

1.20

Jews

1.17

Jew

1.12

 israel

1.12

Activations Density 0.362%

references to Jewish people and related topics

No Comments

No Known Activations