INDEX

Explanations

mentions of Israel and its related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kopp

-0.80

помним

-0.73

 Boyz

-0.73

 Jacoby

-0.72

skyl

-0.69

 Oscill

-0.68

 Mori

-0.68

 Bryant

-0.67

 fabrics

-0.67

 Liar

-0.66

POSITIVE LOGITS

 Israel

1.24

Israel

1.14

 Israeli

1.04

 ISRAEL

1.01

 israel

1.00

RAEL

0.96

Israeli

0.95

 Israël

0.93

 Israelis

0.87

WriteBarrier

0.78

Activations Density 0.121%

mentions of Israel and its related entities

No Comments

No Known Activations